Joydeep Ghosh

Simultaneous Co-clustering and Modeling of Market Data (2008)

Clustering methods for data-mining problems must be extremely scalable. In addition, several data mining applications demand that the clusters obtained be balanced, i.e., be of approximately the same...

Meghana Deodhar, Joydeep Ghosh

Abstract. For difficult prediction problems, practitioners often segment the data into relatively homogenous groups and then build a model for each group. This two-step procedure usually results in...

AUnified Model for Probabilistic Principal Surfaces (2008)

Abstract A Privacy-sensitive Approach to Distributed Clustering (2008)

Principal curves and surfaces are nonlinear generalizations of principal components and subspaces, respectively. They can provide insightful summary of high-dimensional data not typically attainable...

Srujana Merugu, Joydeep Ghosh

While data mining algorithms are often designed to operate on centralized data, in prac-tice data is often acquired and stored in a distributed manner. Centralization of such data before analysis may...

Two-Dimensional Phase Unwrapping Using Neural Networks (2008)

Wade Schwartzkopf, Thomas E. Milner, Joydeep Ghosh, Brian L. Evans, Alan C. Bovik

Imaging systems that construct an image from phase information in received signals include synthetic aperture radar (SAR) and optical Doppler tomography (ODT) systems. A fundamental problem in the...

Hierarchical Density Shaving: A clustering and visualization framework forlarge biological datasets (2008)

Gunjan Gupta, Alexander Liu, Joydeep Ghosh

Abstract In many clustering applications for bioinformatics, onlypart of the data clusters into one or more groups while the rest needs to be pruned. For such situations, we present Hi-erarchical...

CLUSTERING AND VISUALIZATION OF HIGH-DIMENSIONAL BIOLOGICAL DATASETS USING A FAST HMA APPROXIMATION (2008)

Gunjan K. Gupta, Alexander Y. Liu, Joydeep Ghosh

In this paper, we reintroduce Hierarchical Mode Analysis(HMA), which was first proposed in 1968, as a powerful clustering algorithm for bioinformatics. The ability of HMA to find a compact hierarchy...

Bregman Co-clustering and Matrix Approximation A Generalized Maximum Entropy Approach to Bregman Co-clustering and Matrix Approximation (2008)

Arindam Banerjee, Inderjit Dhillon, Joydeep Ghosh, Srujana Merugu, Dharmendra S. Modha

Editor: Co-clustering, or simultaneous clustering of rows and columns of a two-dimensional data matrix, is rapidly becoming a powerful data analysis technique. Co-clustering has enjoyed wide success...

Hierarchical Density Shaving: A clustering and visualization framework for large biological datasets (2008)

Gunjan Gupta, Alexander Liu, Joydeep Ghosh

In many clustering applications for bioinformatics, only part of the data clusters into one or more groups while the rest needs to be pruned. For such situations, we present Hierarchical Density...

Design and Analysis of a "Superscalar" Production System Machine (2008)

A Macroscopic Model of Neural Ensembles II: Frequency Estimation of Oscillations in Coupled Cell Assemblies (2008)

Gains due to the parallel execution of Production Systems have been limited by the need for global synchronization before each rule firing. This synchronization can be eliminated by allowing...

Joydeep Ghosh, Hung-jen Chang, Kadir Liano

This is the second part of a two-part series that applies the macroscopic model of cell assemblies developed in the first part [CGDB91] to analyze the ensemble behavior of coupled sub-populations of...

"Superscalar" Production System Machines: A Proposal with Performance Evaluation (2008)

Nonlinear Memory Functions for Modeling Discrete Time Systems (2008)

Concurrent firing of rules based on the serializability criterion for correctness allows the elimination of unneeded global synchronization in the parallel execution of Production Systems. With this...

Distributed Clustering with Limited Knowledge Sharing (2008)

Certain computational structures consisting of linear temporal encoding stages followed by feedforward neural networks have previously been shown to be universal approximators of causal,...

Joydeep Ghosh, Srujana Merugu

While data mining algorithms invariably operate on centralized data, in practice related information is often acquired and stored at geographically distributed locations due to organizational or...

Top 10 algorithms in data mining (2008)

Wu, Xindong, Kumar, Vipin, Quinlan, J. Ross, Ghosh, Joydeep, Yang, Qiang, Motoda, Hiroshi, ...

Novel strategy for treatment of Japanese encephalitis using arctigenin, a plant lignan (2008)

Swarup, Vivek, Ghosh, Joydeep, Mishra, Manoj Kumar, Basu, Anirban

Objectives To evaluate therapeutic efficacy of arctigenin in an experimental model of Japanese encephalitis (JE). Methods Four- to 5-week-old BALB/c mice of either sex were infected intravenously...

DECISION BOUNDARY FOCUSED NEURAL NETWORK CLASSIFIER (2007)

A Hierarchical Multiclassier System for Hyperspectral Data Analysis Shailesh Kumar 1 (2007)

This paper introduces a novel classier architecture that exploits both support vector concept and the on-line learning of feedforward neural networks. It uses an MLP network to directly determine a...

Joydeep Ghosh, Melba Crawford

Abstract. Many real world classication problems involve high dimensional inputs and a large number of classes. Feature extraction and modular learning approaches can be used to simplify such...

1 Concept-based Clustering of Clickstream Data (2007)

Classification of Hyperspectral Data using Best-bases Feature Extraction Algorithms (2007)

Abstract | Determining the type of a user based on his interaction with a website is a key problem in web usage mining. Absence of proper cookie information makes the task more dicult since one then...

Shailesh Kumar, Joydeep Ghosh, Melba M. Crawford

Mapping landcover type from airborne/spaceborne sensors is an important classification problem in remote sensing. Due to advances in sensor technology, it is now possible to acquire hyperspectral...

Sequence Recognition By Input Anticipation (2007)

Two Stage Habituation Based Neural Networks for Dynamic Signal Classification (2007)

Processing time-dependent information is crucial in a multitude of classification tasks. This paper introduces a new neural network called the anticipation network, which fuses two simple recurrent...

A Versatile Framework for Labelling Imagery With a Large Number of Classes (2007)

This article describes a novel neural network structure designed for the dynamic classification of spatio-temporal signals. The network is a two-stage structure consisting of a biologically motivated...

Shailesh Kumar, Melba Crawford, Joydeep Ghosh

Conventional methods for feature selection use some kind of separability criteria or classification accuracy for computing the relevance of a feature subset to the classification task. In two-class...

A Neural Network Based Classifier and Biofeedback Device for Improving Clarinet Tone-Quality (2007)

Ian R. Fasel, Kurt D. Bollacker, Joydeep Ghosh

This paper describes an automated tool for classifying tone quality (a quality related to timbre). This tool provides real-time visual feedback to players of clarinet to help improve tone production...

Noise Sensitivity Of Static Neural Network Classifiers (2007)

Steven Beck, Joydeep Ghosh

. A variety of artificial neural networks are evaluated for their classification abilities under noisy inputs. These networks include feedforward networks, localized basis function networks and...

Studies on a Network of Complex Neurons (2007)

Robust Classification Techniques For Acoustic Signal Analysis (2007)

In the last decade, much effort has been directed towards understanding the role of chaos in the brain. Work with rabbits reveals that in the resting state the electrical activity on the surface of...

Steven Beck, Larry Deuser, Joydeep Ghosh

Classification of short duration acoustic signals can be very difficult due to the high degree of variability in the signatures. Input feature vectors, resulting from wavelets or short time Fourier...

ANN Based Forecasting of VBR Video Traffic for Dynamic Bandwidth Allocation in ATM Networks (2007)

Estimation of Oscillation Frequency in Coupled Cell Assemblies (2007)

Two time delay neural network (TDNN) based forecasting systems are proposed to perform dynamic bandwidth reservation for real-time, variable bit rate (VBR) video service in ATM networks. Both...

Joydeep Ghosh, Hung-jen Chang, Kadir Liano

A macroscopic model of cell assemblies is used to analyze the ensemble behavior of coupled sub-populations of inhibitory and excitatory neurons. For such systems, rhythmic behavior can occur even in...

The M-Cache: A Message-Handling Mechanism for Multicomputer Systems (2007)

Jeffrey Draper, Joydeep Ghosh

This paper presents the design and evaluation of the M-cache, a small, fast and intelligent memory for handling messages at the processing nodes of multicomputer systems. The M-cache is neither a...

Stirling Networks: A Versatile Combinatorial Topology for Multiprocessor Systems (2007)

Sajal Das, Joydeep Ghosh, Narsingh Deo, North Texas

We derive a family of labeled, undirected graphs from the Stirling table of the first kind and investigate properties of these graphs as a basis for multiprocessor interconnection networks. The...

Efficient Transport of Real-time VBR Video over ATM via Dynamic Bandwidth Allocation (2007)

On Supporting Rule-Based Image Interpretation Using a Distributed Memory Multicomputer (2007)

This paper presents a novel approach to dynamic transmission bandwidth allocation for transport of real-time variable-bit-rate video in ATM networks. Describe video traffic in the frequency domain:...

W. J. Maas, Chen-Chau Chu, Joydeep Ghosh, J. K. Aggarwal

High-level tasks in image understanding are similar to many AI problems in terms of complexity and solution techniques. In particular, rule based systems have been employed for image interpretation...

Structurally Adaptive Localized Mixtures of Experts for Non-Stationary Environments (2007)

Sequence Learning with Recurrent Networks: Analysis of Internal Representations (2007)

This paper introduces a neural network capable of dynamically adapting its architecture to realize time variant non-linear input-output maps. This network has its roots in the mixture of experts...

Joydeep Ghosh, Vijay Karamcheti

. The recognition and learning of temporal sequences is fundamental to cognitive processing. Several recurrent networks attempt to encode past history through feedback connections from "context...

OTA based Neural Network Architectures with On-Chip Tuning of Synapses (2007)

Joydeep Ghosh, Patrick Lacour, Spence Jackson

. We propose and analyze analog VLSI implementations of neural networks in which both the neural cells and the synapses are realized using Operational Transconductance Amplifiers (OTAs). These...

defOn Supporting Rule-Based Image Interpretation Using a Distributed Memory Multicomputer (2007)

W. J. Maas, Chen-Chau Chu, Joydeep Ghosh, J. K. Aggarwal

High-level tasks in image understanding are similar to many AI problems in terms of complexity and solution techniques. In particular, rule based systems have been employed for image interpretation...

The M-Cache: A Message-Handling Mechanism for Multicomputer Systems (2007)

Jeffrey Draper, Joydeep Ghosh

This paper presents the design and evaluation of the M-cache, a small, fast and intelligent memory for handling messages at the processing nodes of multicomputer systems. The M-cache is neither a...

Serializability Improves Parallel Execution of Production System (2007)

Signal Representation Assignment for an N-Value Simulator (2007)

This paper presents a new production system architecture that uses serializability as a correctness criterion to select a set of productions to be executed in parallel. The use of serializability...

Jos'e Nelson, Jos'e Nelson Amaral, Joydeep Ghosh

In a gate level n-value compiled simulator, the time necessary to propagate a given signal through a gate is of fundamental importance for the speed of the system. This propagation time is minimized...

Generalized Associative Mixture of Experts (2007)

Shailesh Kumar, Joydeep Ghosh

Modular learning, inspired by divide and conquer, learns a large number of localized simple concepts (classifiers or function approximators) as against single complex global concept. As a result,...

Polyline feature extraction for land cover classification using hyperspectral data (2007)

Re Henneguelle, Joydeep Ghosh, Melba Crawford

Abstract. Prediction of landcover types from airborne/spaceborne sensors is an important classification problem in remote sensing. Due to recent advances in sensor technology, it is now possible to...

Acknowledgments (2007)

James A. Bednar, Risto Miikkulainen Supervisor, Wilson S. Geisler, Raymond Mooney, Benjamin Kuipers, Joydeep Ghosh, ...

Copyright by

Acknowledgments (2007)

C. Greg Plaxton, Annamaria Nina Amenta, Inderjit Dhillon, Anna Gál, Joydeep Ghosh, Ramgopal Reddy Mettu, ...

During my graduate career, there were many individuals that helped me become a better researcher as well as a better person. First and foremost, I would like to express my gratitude to my advisor...

Shailesh Kumar, Joydeep Ghosh, Melba M. Crawford

Abstract: Many classification problems involve high dimensional inputs and a large number of classes. Multiclassifier fusion approaches to such difficult problems typically centre around smart...

Acknowledgments (2007)

Risto Miikkulainen Supervisor, Wilson S. Geisler, Raymond Mooney, Benjamin Kuipers, Joydeep Ghosh, Les Cohen, ...

This thesis would not have been possible without the support, advice, and encouragement of Risto Miikkulainen over the years, not to mention all his work on the draft revisions. If by some stroke of...

Cultural Enhancement of Neuroevolution Committee: (2007)

Paul H. Mcquesten, Risto Miikkulainen Supervisor, Joydeep Ghosh, Benjamin Kuipers, Raymond Mooney, Bruce Porter, ...

Copyright by

Complete memory structures for approximating nonlinear discrete time mappings (2007)

Bryan W. Stiles, Irwin W. S, Joydeep Ghosh

This paper introduces a general structure that is capable of approximating input-output maps of nonlinear discrete-time systems. The structure is comprised of two stages, a dynamical stage followed...

Knowledge Reuse Mechanisms for Categorizing Related Image Sets (2007)

Equalization for Discrete Multitone Transceivers Approved by Dissertation Committee: (2007)

Abstract. This chapter introduces the concept of classier knowledge reuse as a means of exploiting domain knowledge taken from old, previously created, relevant classi ers to assist in a new...

Guner Arslan, Guner Arslan, Brian L. Evans, Ross Baldick, Alan C. Bovik, Joydeep Ghosh, ...

to my wife and my parents with love Acknowledgments I have a long list of people to thank for their sincere support and help. I would like to start with my parents Selime and Cemal Arslan. They are...

ESTIMATION AND EQUALIZATION APPROVED BY (2007)

Biao Lu, Brian L. Evans, Alan C. Bovik, Joydeep Ghosh, Risto Miikkulainen, Lloyd D. Clark

Copyright by

Chapter 1 Speeding Up Production Systems: From Concurrent Matching to Parallel Rule Firing (2007)

L. Kanal, V. Kumar, H. Kitano, C. Suttner, Jos'e Nelson Amaral, Joydeep Ghosh

This chapter identifies the problems that a computer architect faces in attempting to speed up the execution of production systems. We first focus on state-saving algorithms using Rete networks...

Scalable, Balanced Model-based Clustering (2007)

Expectation Maximization for Clustering on Hyperspheres (2007)

This paper presents a general framework for adapting any generative (model-based) clustering algorithm to provide balanced solutions, i.e., clusters of comparable sizes. Partitional, model-based...

Arindam Banerjee Inderjit, Arindam Banerjee, Inderjit Dhillon, Joydeep Ghosh, Suvrit Sra

High dimensional directional data is becoming increasingly important in contemporary applications such as analysis of text and gene-expression data. A natural model for multi-variate directional data...

Mean Model Clustering (2007)

Arindam Banerjee And, Arindam Banerjee, Joydeep Ghosh

this paper, an effective and efficient model-based 2-clustering approach using Fisher kernel based similarities [2][3] is proposed. The Fisher kernel is derived from the knowledge of the family of...

Polyline Feature Extraction for Land Cover (2007)

Classification Using Hyperspectral, Re Henneguelle, Joydeep Ghosh, Melba Crawford

Prediction of landcover types from airborne/spaceborne sensors is an important classification problem in remote sensing. Due to recent advances in sensor technology, it is now possible to acquire...

Expectation Maximization for Clustering on Hyperspheres (2007)

Arindam Banerjee Inderjit, Arindam Banerjee, Inderjit S. Dhillon, Joydeep Ghosh, Suvrit Sra

High dimensional directional data is becoming increasingly important in contemporary applications such as analysis of text and gene-expression data. A natural model for multi-variate directional data...

Machine Learning: Problems (2007)

Inderjit S. Dhillon, Jason Davis, Joydeep Ghosh, Brian Kulis, Srujana Merugu, ...

Clustering: group a set of data objects Co-clustering: simultaneously partition data objects & features Matrix Approximation SVD: low-rank approximation, minimizes Frobenius error NNMA: low-rank...

A framework for simultaneous co-clustering and learning from complex data (2007)

Meghana Deodhar, Joydeep Ghosh

For difficult classification or regression problems, practitioners often segment the data into relatively homogenous groups and then build a model for each group. This two-step procedure usually...

From Named Entity Recognition and Disambiguation To Relation Extraction (2007)

Razvan Constantin Bunescu, Raymond J. Mooney, Inderjit S. Dhillon, Joydeep Ghosh, Andrew Mccallum, Bruce Porter, ...

certifies that this is the approved version of the following dissertation:

Following Natural Language Route Instructions Committee: (2007)

Matthew Tierney Macmahon, Benjamin J. Kuipers, Joydeep Ghosh, Jonas Kuhn, Dewayne E. Perry, Brian J. Stankiewicz

To my parents, Paul and B.J., for encouraging both wonder and accomplishment. To my wife, Sarah, for her unflagging love, support, and understanding. To all my friends, who have helped in innumerable...

Robust Structure-Based Autonomous Color Learning (2007)

Mohan Sridharan, Benjamin Kuipers Supervisor, Peter Stone Supervisor, Joydeep Ghosh, Alan Bovik, Gregory Dudek

Dedicated to the children around the world. If only they could retain their inquisitiveness forever and continue to dream fearlessly... Acknowledgments I would like to thank Dr. Peter Stone and Dr....

U.S.A. (2007)

Meghana Deodhar, Joydeep Ghosh, C Meghana Deodhar, Joydeep Ghosh

For difficult classification or regression problems, practitioners often segment the data into relatively homogenous groups and then build a model for each group. This two-step procedure usually...

Task Encoding, Motion Planning and Intelligent Control using Qualitative Models (2007)

Subramanian Ramamoorthy, Benjamin J. Kuipers, Aristotle Arapostathis, Mircea D. Driga, Joydeep Ghosh, Subramanian Ramamoorthy

Dedicated to the spirit of free inquiry Acknowledgments A wise man 1 said “ If you have built castles in the air, your work need not be lost; that is where they should be. Now put the foundations...

Bregman Bubble Co-clustering (2007)

Meghana Deodhar, Hyuk Cho, Gunjan Gupta, Joydeep Ghosh, Inderjit Dhillon

Clustering problems often involve datasets where only a part of the data is relevant to the problem e.g. in microarray data analysis only a subset of the genes show interesting patterns within a...

From Named Entity Recognition and Disambiguation To Relation Extraction (2007)

Razvan Constantin Bunescu, Raymond J. Mooney, Inderjit S. Dhillon, Joydeep Ghosh, Andrew Mccallum, Bruce Porter, ...

certifies that this is the approved version of the following dissertation:

Sudden cardiac death in athletes - what can be done? (2006)

Ghosh, Joydeep

Sudden death in athletes is a rare event but brings with it an impact that goes beyond sport. There are many causes of sudden death during exercise. While the responsibility of preventing or treating...

Evolving Visibly Intelligent Behavior for Embedded Game Agents (2006)

Bobby D. Bryant, Bobby Don Bryant, Risto Miikkulainen Supervisor, Joydeep Ghosh, Benjamin Kuipers, Raymond Mooney, ...

Copyright by

Bregman Bubble Clustering: A Robust Framework for Mining Dense Clusters (2006)

Gunjan Gupta, Joydeep Ghosh, C Gunjan Gupta, Joydeep Ghosh

In classical clustering, each data point is assigned to at least one cluster. However, in many applications only a small subset of the available data is relevant for the problem and the rest needs to...

Automatic construction of n-ary tree based taxonomies (2006)

Kunal Punera, Suju Rajan, Joydeep Ghosh

Hierarchies are an intuitive and effective organization paradigm for data. Of late there has been considerable research on automatically learning hierarchical organizations of data. In this paper, we...

Bregman bubble clustering: A robust, scalable framework for locating multiple, dense regions in data (2006)

Gunjan Gupta, Joydeep Ghosh

In traditional clustering, every data point is assigned to at least one cluster. On the other extreme, One Class Clustering algorithms proposed recently identify a single dense cluster and consider...

Predicting Stock Price from Financial Message Boards with a Mixture of Experts Framework (2006)

Alexander Y Liu, Bin Gu, Prabhudev Konana, Joydeep Ghosh

aliu [at] ece.utexas.edu bin.gu [at] mccombs.utexas.edu prabhudev.konana [at] mccombs.utexas.edu ghosh [at] ece.utexas.edu

Automated Hierarchical Density Shaving and Gene DIVER (2006)

Gunjan Gupta, Alexander Liu, Joydeep Ghosh, C Gunjan Gupta, Er Liu, Joydeep Ghosh

A key application of clustering data obtained from sources such as microarray, protein mass spectroscopy, and phylogenetic profile is the detection of functionally related genes. Typically, only a...

Role of implantable cardioverter defibrillators in the treatment of hypertrophic cardiomyopathy (2005)

Ghosh, Joydeep, Francis, Johnson, Maron, Barry J.

Hypertrophic cardiomyopathy (HCM) is an important cardiovascular disease with sudden cardiac death as the most devastating presentation. Implantable cardioverter defibrillators (ICD) are the optimal...

Risk stratification for sudden cardiac death In patients with non-ischemic dilated cardiomyopathy (2005)

Shekha, Karthik, Ghosh, Joydeep, Thekkoott, Deepak, Greenberg, Yisachar

Non ischemic dilated cardiomyopathy (NIDCM) is a disorder of myocardium. It has varying etiologies. Albeit the varying etiologies of this heart muscle disorder, it presents with symptoms of heart...

No-reference quality assessment using natural scene statistics: JPEG2000 (2005)

Alan C. Bovik, Lawrence K. Cormack, J. K. Aggarwal, Chandrajit Bajaj, Gustavo De Veciana, Joydeep Ghosh, ...

In the name of Allah, most Gracious, ever Merciful This work is a humble offering to The Grace that is my Lord The love that are my parents The joy that is my family The wealth that is my health The...

Statistical Analysis and Selection of Visual Fixations (2005)

Umesh Rajashekar, Alan C. Bovik, Lawrence K. Cormack, J. K. Aggarwal, Wilson S. Geisler, Joydeep Ghosh, ...

Dedicated to my wonderful friends at LIVE.

Automatically Learning Document Taxonomies for Hierarchical Classification (2005)

Kunal Punera, Suju Rajan, Joydeep Ghosh

While several hierarc hic al c assific ation methods have been applied to web c ntent, suc htec hniques invariably rely on a pre-defined taxonomy of doc uments. We propose a new tec hnique that...

Robust One-Class Clustering Using Hybrid . . . (2005)

Gunjan Gupta, Joydeep Ghosh

Unsupervised learning methods often involve summarizing the data using a small number of parameters. In certain domains, only a small subset of the available data is relevant for the problem....

Robust One-Class Clustering Using Hybrid Global and Local Search (2005)

Gunjan Gupta, Joydeep Ghosh

Unsupervised learning methods often involve summarizing the data using a small number of parameters. In certain domains, only a small subset of the available data is relevant for the problem....

Model-based overlapping clustering (2005)

Arindam Banerjee, Chase Krumpelman, Joydeep Ghosh

While the vast majority of clustering algorithms are partitional, many real world datasets have inherently overlapping clusters. Several approaches to finding overlapping clusters have come from work...

Clump: A scalable and robust framework for structure discovery (2005)

C Kunal Punera, Kunal Punera, Joydeep Ghosh, Joydeep Ghosh

We introduce a robust and efficient framework called CLUMP (CLustering Using Multiple Prototypes) for unsupervised discovery of structure in data. CLUMP relies on finding multiple prototypes that...

Clustering on the unit hypersphere using von mises-fisher distributions (2005)

Arindam Banerjee, Inderjit S. Dhillon, Joydeep Ghosh, Suvrit Sra, Greg Ridgeway

Several large scale data mining applications, such as text categorization and gene expression analysis, involve high-dimensional data that is also inherently directional in nature. Often such data is...

Acknowledgments (2005)

Prem Noel Melville, Raymond J. Mooney, Benjamin Kuipers, Peter Stone, Joydeep Ghosh, Jude Shavlik, ...

To my loving parents.

Model-based overlapping clustering (2005)

Arindam Banerjee, Chase Krumpelman, Joydeep Ghosh

While the vast majority of clustering algorithms are partitional, many real world datasets have inherently overlapping clusters. The recent explosion of analysis on biological datasets, which are...

Acknowledgments (2005)

Prem Noel Melville, Raymond J. Mooney, Benjamin Kuipers, Peter Stone, Joydeep Ghosh, Jude Shavlik, ...

To my loving parents.

Acknowledgments (2005)

Sugato Basu, Raymond J. Mooney, Inderjit S. Dhillon, Joydeep Ghosh, C. Gregory Plaxton, Mehran Sahami

In loving memory of my grandparents

Generative model-based document clustering: a comparative study (2005)

This thesis is dedicated to my mother and the greatest influence on my life, Late Mrs. (2005)

This paper presents a detailed empirical study of twelve generative approaches to text clustering obtained by applying four types of document-to-model assignment strategies (hard, stochastic, soft...

Vishal Monga, Brian L. Evans, Ross Baldick, Wilson S. Geisler, John E. Gilbert, Joydeep Ghosh, ...

I would like to begin by thanking my parents, albeit I understand any amount of gratitude shown to them is woefully inadequate. My father’s unconditional support is largely the reason that this PhD...

Clustering on the unit hypersphere using von mises-fisher distributions (2005)

Arindam Banerjee, Inderjit S. Dhillon, Joydeep Ghosh, Suvrit Sra, Greg Ridgeway

Several large scale data mining applications, such as text categorization and gene expression analysis, involve high-dimensional data that is also inherently directional in nature. Often such data is...

Exploiting class hierarchies for knowledge transfer in hyperspectral data (2005)

Suju Rajan, Joydeep Ghosh

Abstract. Obtaining ground truth for hyperspectral data is an expensive task. In addition, a number of factors cause the spectral signatures of the same class to vary with location and/or time....

A generalized maximum entropy approach to bregman co-clustering and matrix approximation (2004)

Arindam Banerjee, Inderjit Dhillon, Joydeep Ghosh, Srujana Merugu

Co-clustering is a powerful data mining technique with varied applications such as text clustering, microarray analysis and recommender systems. Recently, an informationtheoretic co-clustering...

Adaptive Feature Selection for Hyperspectral Data Analysis (2004)

Donna Korycinski, Melba Crawford, J. W. Barnes, Joydeep Ghosh

Abstract- High dimensional inputs coupled with scarcity of labeled data are among the greatest challenges for classification of hyperspectral data. These problems are exacerbated if the number of...

Automated Stock Trading (2004)

Harish K Subramanian, Harish K Subramanian, Peter Stone, Benjamin Kuipers, Joydeep Ghosh, Harish K Subramanian, ...

Acknowledgements I would like to express my deep gratitude to Dr. Peter Stone for his guidance, advice, and encouragement. It has been great fun and a privilege to conduct research under his...

This thesis is dedicated to my (2004)

Serene Banerjee, Brian L. Evans, Ross Baldick, Alan C. Bovik, Wilson S. Geisler, Joydeep Ghosh, ...

On completing this dissertation my special thanks goes to my Mother. With her constant inspiration, she always stood up to be a role model that I could follow. Her constant sacrifice to ensure each...

A generalized maximum entropy approach to bregman co-clustering and matrix approximation (2004)

Arindam Banerjee, Inderjit Dhillon, Joydeep Ghosh, Srujana Merugu

Outlink Estimation for Pagerank Computation under Missing Data (2004)

Outlink Estimation for Pagerank Computation under Missing Data (2004)

The enormity and rapid growth of the web-graph forces quantities such as its pagerank to be computed under significant amount of missing information consisting mainly of outlinks of pages that have...

Outlink Estimation for Pagerank Computation under Missing Data (2004)

The enormity and rapid growth of the web-graph forces quantities such as its pagerank to be computed under missing information consisting of outlinks of pages that have not yet been crawled. This...

An Information Theoretic Analysis of Maximum Likelihood Mixture Estimation for Exponential Families (2004)

The enormity and rapid growth of the web-graph forces quantities such as its pagerank to be computed under significant amount of missing information consisting mainly of outlinks of pages that have...

Arindam Banerjee, Inderjit Dhillon, Joydeep Ghosh, Srujana Merugu

An important task in unsupervised learning is maximum likelihood mixture estimation (MLME) for exponential families. In this paper, we prove a mathematical equivalence between this MLME problem and...

Clustering with Bregman Divergences (2004)

Arindam Banerjee, Srujana Merugu, Inderjit Dhillon, Joydeep Ghosh

A wide variety of distortion functions are used for clustering, e.g., squared Euclidean distance, Mahalanobis distance and relative entropy. In this paper, we propose and analyze parametric hard and...

A generalized maximum entropy approach to bregman co-clustering and matrix approximation (2004)

Arindam Banerjee, Inderjit Dhillon, Joydeep Ghosh, Srujana Merugu

Co-clustering is a powerful data mining technique with varied applications such as text clustering, microarray analysis and recommender systems. Recently, an informationtheoretic co-clustering...

Clustering with Bregman divergences (2004)

Arindam Banerjee, Srujana Merugu, Inderjit Dhillon, Joydeep Ghosh

A wide variety of distortion functions are used for clustering, e.g., squared Euclidean distance, Mahalanobis distance and relative entropy. In this paper, we propose and analyze parametric hard and...

Frequency sensitive competitive learning for balanced clustering on high-dimensional hyperspheres (2004)

Arindam Banerjee, Joydeep Ghosh, Senior Member

Abstract — Competitive learning mechanisms for clustering in general suffer from poor performance for very high dimensional ( ¢¡¤£¥£¦ £ ) data because of “curse of dimensionality ”...

Clustering with Bregman divergences (2004)

Arindam Banerjee, Srujana Merugu, Inderjit S. Dhillon, Joydeep Ghosh, John Lafferty

A wide variety of distortion functions, such as squared Euclidean distance, Mahalanobis distance, Itakura-Saito distance and relative entropy, have been used for clustering. In this paper, we propose...

A generalized maximum entropy approach to bregman co-clustering and matrix approximation (2004)

Arindam Banerjee, Inderjit Dhillon, Joydeep Ghosh, Srujana Merugu, Dharmendra S. Modha, John Lafferty

Co-clustering, or simultaneous clustering of rows and columns of a two-dimensional data matrix, is rapidly becoming a powerful data analysis technique. Co-clustering has enjoyed wide success in...

An empirical comparison of hierarchical vs. two-level approaches to multiclass problems (2004)

Suju Rajan, Joydeep Ghosh

Abstract. The ECOC framework provides a powerful and popular method for solving multiclass problems using a multitude of binary classifiers. We had recently introduced the Binary Hierarchical...

An information theoretic analysis of maximum likelihood mixture estimation for exponential families (2004)

Arindam Banerjee, Inderjit Dhillon, Joydeep Ghosh, Srujana Merugu

An important task in unsupervised learning is maximum likelihood mixture estimation (MLME) for exponential families. In this paper, we prove a mathematical equivalence between this MLME problem and...

Clustering with Bregman divergences (2004)

Arindam Banerjee, Srujana Merugu, Inderjit S. Dhillon, Joydeep Ghosh, John Lafferty

A wide variety of distortion functions, such as squared Euclidean distance, Mahalanobis distance, Itakura-Saito distance and relative entropy, have been used for clustering. In this paper, we propose...

Relationship-based clustering and visualization for high-dimensional data mining (2003)

Alexander Strehl, Joydeep Ghosh

n several real-life data-mining applications, data reside in very high (1000 or more) dimen-sional space, where both clustering techniques developed for low-dimensional spaces (k-means, BIRCH,...

A unified framework for model-based clustering (2003)

A maximum entropy framework for higher order link analysis on directed graphs (2003)

Model-based clustering techniques have been widely used and have shown promising results in many applications involving complex data. This paper presents a unified framework for probabilistic...

Context-Sensitive Modeling of Web-Surfing Behaviour using Concept Trees (2003)

Link-analysis based techniques for ranking of the vertices of a directed graph have been widely studied in the social networks and bibliometrics communities. More recently, they have been popularized...

A unified framework for model-based clustering (2003)

Early approaches to mathematically abstracting websurfing behavior were largely based on first-order Markov models. Most humans however do not surf in a "memoryless " fashion, rather they...

Raymond J. Mooney, William W. Cohen, Inderjit S. Dhillon, Joydeep Ghosh, Peter H. Stone, Mikhail Yuryevich Bilenko, ...

To my dear grandparents

Shi Zhong, Joydeep Ghosh, Claire Cardie

Model-based clustering techniques have been widely used and have shown promising results in many applications involving complex data. This paper presents a unified framework for probabilistic...

Expectation Maximization for Clustering on Hyperspheres (2003)

Arindam Banerjee, Inderjit Dhillon, Joydeep Ghosh, Suvrit Sra

High dimensional directional data is becoming increasingly important in contemporary applications such as analysis of text and gene-expression data. A natural model for multi-variate directional data...

A Comparative Study of Generative Models for Document Clustering (2003)

Scalable Clustering (2003)

Generative models based on the multivariate Bernoulli and multinomial distributions have been widely used for text classification. Recently, the spherical k-means algorithm, which has desirable...

Joydeep Ghosh, Nong Ye (ed, Partitional Methods

Contents 1 Introduction 3 2 Clustering Techniques: A Brief Survey 4 2.1 Partitional Methods . . . . . . . . . . . . . . . . . . . . . . . . . . . 6 2.2 Hierarchical Methods . . . . . . . . . . . . ....

Generative Model-based Clustering of Directional Data (2003)

Arindam Banerjee, Inderjit Dhillon, Joydeep Ghosh, Suvrit Sra

High dimensional directional data is becoming increasingly important in contemporary applications such as analysis of text and gene-expression data. A natural model for multivariate directional data...

Under consideration for publication in Knowledge and Information Systems Generative Model-based Document Clustering: A Comparative Study (2003)

Context-Sensitive Modeling of Web-Surfing Behaviour using Concept Trees (2003)

Abstract. This paper presents a detailed empirical study of twelve generative approaches to text clustering, obtained by applying four types of document-to-cluster assignment strategies (hard,...

A consensus framework for integrating distributed clusterings under limited knowledge sharing (2002)

Early approaches to mathematically abstracting web-surfing behavior were largely based on first-order Markov models. Most humans however do not surf in a "memoryless " fashion, rather they...

Joydeep Ghosh, Alexander Strehl, Srujana Merugu

This paper examines the problem of combining multiple partitionings of a set of objects into a single consolidated clustering without accessing the features or algorithms that determined these...

Cultural Enhancement of Neuroevolution (2002)

Paul Herbert Mcquesten, Risto Miikkulainen Supervisor, Joydeep Ghosh, Benjamin Kuipers, Raymond Mooney, Bruce Porter, ...

Some of the notions of the functions of culture which lead to this work were the product of extensive discussions with Dr. Pamela McQuesten, to whom I have the honor and joy of being married. Her...

Classification of Multi-spectral Chromosome Images Publication No._____________ (2002)

Wade Carl Schwartzkopf, Brian L. Evans, Alan C. Bovik, Kenneth R. Castleman, Joydeep Ghosh, Thomas E. Milner, ...

This dissertation develops new methods for automatic chromosome identification by taking advantage of the multispectral information in M-FISH chromosome images and by jointly performing chromosome...

Cluster ensembles - a knowledge reuse framework for combining multiple partitions (2002)

Alexander Strehl, Joydeep Ghosh, Claire Cardie

This paper introduces the problem of combining multiple partitionings of a set of objects into a single consolidated clustering without accessing the features or algorithms that determined these...

On scaling up balanced clustering algorithms (2002)

Cluster ensembles - a knowledge reuse framework for combining multiple partitions (2002)

"rand01 "-- 2003/4/14-- 10:12-- page 1-- #1 i i i i

Alexander Strehl, Joydeep Ghosh, Claire Cardie

This paper introduces the problem of combining multiple partitionings of a set of objects into a single consolidated clustering without accessing the features or algorithms that determined these...

Cluster ensembles - a knowledge reuse framework for combining multiple partitions (2002)

Er Strehl, Joydeep Ghosh

It is widely recognized that combining multiple classification or regression models typically provides superior results compared to using a single, well-tuned model. However, there are no well known...

A consensus framework for integrating distributed clusterings under limited knowledge sharing (2002)

Joydeep Ghosh, Alexander Strehl, Srujana Merugu

This paper examines the problem of combining multiple partitionings of a set of objects into a single consolidated clustering without accessing the features or algorithms that determined these...

Multiclassifier systems: Back to the future (2002)

Joydeep Ghosh

Abstract. While a variety of multiple classifier systems have been studied since at least the late 1950’s, this area came alive in the 90’s with significant theoretical advances as well as...

Cluster ensembles - a knowledge reuse framework for combining multiple partitions (2002)

Alexander Strehl, Joydeep Ghosh, Claire Cardie

This paper introduces the problem of combining multiple partitionings of a set of objects into a single consolidated clustering without accessing the features or algorithms that determined these...

Frequency Sensitive Competitive Learning for Clustering on High-dimensional Hyperspheres (2002)

Robust Combining of Disparate Classifiers through Order Statistics (2002)

This paper derives three competitive learning mechanisms from first principles to obtain clusters of comparable sizes when both inputs and representatives are normalized. These mechanisms are very...

Raymond J. Mooney, Joydeep Ghosh

Integrating the outputs of multiple classifiers via combiners or meta-learners has led to substantial improvements in several difficult pattern recognition problems. In this article, we investigate a...

Acknowledgments (2002)

Ramgopal Reddy Mettu, C. Greg Plaxton, Annamaria Nina Amenta, Inderjit Dhillon, Anna Gál, Joydeep Ghosh, ...

During my graduate career, there were many individuals that helped me become a better researcher as well as a better person. First and foremost, I would like to express my gratitude to my advisor...

Acknowledgments (2002)

To my mother.

Increasing PageRank through Reinforcement (2002)

Learning Adrian Agogino, Adrian K. Agogino, Joydeep Ghosh

This paper describes a reinforcement learning method, derived from collective intelligence principles, for increasing the combined PageRank for a set of domains. This increased rank is achieved...

Abstract (2002)

On scaling up balanced clustering algorithms (2002)

Integrating the outputs of multiple classifiers via combiners or meta-learners has led to substantial improvements in several difficult pattern recognition problems. In this article we investigate a...

Detecting seasonal trends and cluster motion visualization for very high dimensional transactional data (2001)

Transactional Data, Gunjan K Gupta, Joydeep Ghosh

Real life transactional data often poses challenges such as very large size, high dimensionality, skewed distribution, sparsity, seasonal variations and market-drift or migration [1, 2]. Most studies...

A unified model for probabilistic principal surfaces (2001)

Perceptual Grouping in a Self-Organizing Map of Spiking Neurons (2001)

AbstractÐPrincipal curves and surfaces are nonlinear generalizations of principal components and subspaces, respectively. They can provide insightful summary of high-dimensional data not typically...

Risto Miikkulainen Supervisor, Benjamin J. Kuipers, Raymond J. Mooney, Wilson S. Geisler, Joydeep Ghosh, Yoonsuck Choe, ...

This document is a reformatted version of the original dissertation. Copyright by

Clickstream Clustering Using Weighted Longest Common Subsequences (2001)

Detecting seasonal trends and cluster motion visualization for very high dimensional transactional data (2001)

Categorizing visitors based on their interactions with a website is a key problem in web usage mining. The clickstreams generated by various users often follow distinct patterns, the knowledge of...

Gunjan K Gupta, Joydeep Ghosh

Real life transactional data often poses challenges such as very large size, high dimensionality, skewed distribution, sparsity, seasonal variations and market-drift or migration [1, 2]. Most studies...

Perceptual Grouping in a Self-Organizing Map of Spiking Neurons (2001)

Risto Miikkulainen Supervisor, Benjamin J. Kuipers, Raymond J. Mooney, Wilson S. Geisler, Joydeep Ghosh, Yoonsuck Choe, ...

This document is a reformatted version of the original dissertation. Copyright by

Evaluating the novelty of text-mined rules using lexical knowledge (2001)

Sugato Basu, Raymond J. Mooney, Krupakar V. Pasupuleti, Joydeep Ghosh

A data-mining system may discover a large body of rules; however, relatively few of these may convey useful new knowledge to the user. Several metrics for evaluating the \interestingness" of...

Evaluating the novelty of text-mined rules using lexical knowledge (2001)

Sugato Basu, Raymond J. Mooney, Krupakar V. Pasupuleti, Joydeep Ghosh

In this paper, we present a new method of estimating the novelty of rules discovered by data-mining methods using WordNet, a lexical knowledge-base of English words. We assess the novelty of a rule...

Value Balanced Agglomerative Connectivity Clustering (2001)

Gunjan K Gupta, Joydeep Ghosh

In this paper we propose a new clustering framework for transactional data-sets involving large numbers of customers and products. Such transactional data pose particular issues such as very high...

Clickstream Clustering Using Weighted Longest Common Subsequences (2001)

Robust Combining of Disparate Classifiers through Order Statistics (2001)

Categorizing visitors based on their interactions with a website is a key problem in web usage mining. The clickstreams generated by various users often follow distinct patterns, the knowledge of...

Using Lexical Knowledge to Evaluate the Novelty of Rules Mined from Text (2001)

Integrating the outputs of multiple classifiers via combiners or meta-learners has led to substantial improvements in several difficult pattern recognition problems. In this article we investigate a...

Sugato Basu, Raymond J. Mooney, Krupakar V. Pasupuleti, Joydeep Ghosh

We present a novel application of WordNet to estimating the interestingness of rules discovered by data-mining methods. We estimate the novelty of text-mined rules using semantic distance measures...

Appears in Proceedings of the Seventh International Converence on Knowledge Discovery and Data Mining (2001)

Sugato Basu, Raymond J. Mooney, Krupakar V. Pasupuleti, Joydeep Ghosh

In this paper, we present a new method of estimating the novelty of rules discovered by data-mining methods using WordNet, a lexical knowledge-base of English words. We assess the novelty of a rule...

Value Balanced Agglomerative Connectivity Clustering (2001)

Gunjan K. Gupta, Joydeep Ghosh

There are various issues with transactional data such as high dimensionality (> 10; 000), sparsity (often a customer has any product in common with only 1% or less of remaining customers) and the...

Perceptual Grouping in a Self-Organizing Map of Spiking Neurons (2001)

Risto Miikkulainen Supervisor, Benjamin J. Kuipers, Raymond J. Mooney, Wilson S. Geisler, Joydeep Ghosh, Yoonsuck Choe, ...

This document is a reformatted version of the original dissertation. Copyright by

Detecting seasonal trends and cluster motion visualization for very high dimensional transactional data (2001)

Gunjan K. Gupta, Joydeep Ghosh

Real-life transactional data-sets often involve millions of customers and thousands of products, recorded over a period of time. Typical marketbasket tools try to use the full data or a random...

Value Balanced Agglomerative Connectivity Clustering (2001)

Gunjan K. Gupta, Joydeep Ghosh

There are various issues with transactional data such as high dimensionality ( ¢¡¤£¦¥§£¨£¨ £), sparsity (often a customer has any product in common with only ¡�© or less of...

A unified model for probabilistic principal surfaces (2001)

Best-Bases Feature Extraction Algorithms for (2001)

AbstractÐPrincipal curves and surfaces are nonlinear generalizations of principal components and subspaces, respectively. They can provide insightful summary of high-dimensional data not typically...

Classification Of Hyperspectral, Shailesh Kumar, Joydeep Ghosh, Melba M. Crawford

Due to advances in sensor technology, it is now possible to acquire hyperspectral data simultaneously in hundreds of bands. Algorithms that both reduce the dimensionality of the data sets and handle...

ªThree-Dimensional Model-Based Object Recognition and Pose Estimation Using (2000)

Er Strehl, Joydeep Ghosh, Raymond Mooney

A novel scheme using spherical manifolds is proposed for the simultaneous classification and pose estimation of 3-D objects from 2-D images. The spherical manifold imposes a local topological...

Clustering of web documents enables (semi-)automated categorization, and facilitates certain types of search. Any clustering method has to embed the documents in a suitable similarity space. While...

Multiresolution Feature Extraction for Pairwise Classification of Hyperspectral Data (2000)

Shailesh Kumar, Joydeep Ghosh, Melba M. Crawford

Prediction of landcover type from airborne/spaceborne sensors is an important classification problem in remote sensing. Due to advances in sensor technology, it is now possible to acquire...

A Scalable Approach to Balanced, High-dimensional Clustering of Market-baskets (2000)

Alexander Strehl, Er Strehl, Joydeep Ghosh

This paper presents Opossum, a novel similarity-based clustering approach based on constrained, weighted graph-partitioning. Opossum is particularly attuned to real-life market baskets, characterized...

Clustering Guidance And Quality Evaluation Using Relationship-Based Visualization (2000)

Alexander Strehl, Joydeep Ghosh

In this paper, we introduce Clusion, a clustering visualization toolkit, that facilitates data exploration and validation of clustering results. Clusion is especially suitable for very...

Alexander Strehl Joydeep, Er Strehl, Joydeep Ghosh, Raymond Mooney

Clustering of web documents enables (semi-)automated categorization, and facilitates certain types of search. Any clustering method has to embed the documents in a suitable similarity space. While...

Alexander Strehl, Er Strehl, Joydeep Ghosh, Raymond Mooney

Clustering of web documents enables (semi-)automated categorization, and facilitates certain types of search. Any clustering method has to embed the documents in a suitable similarity space. While...

Value-based Customer Grouping from Large Retail Data-sets (2000)

Alexander Strehl, Er Strehl, Joydeep Ghosh

In this paper, we propose OPOSSUM, a novel similarity-based clustering algorithm using constrained, weighted graph-partitioning. Instead of binary presence or absence of products in a market-basket,...

A Bayesian Pairwise Classifier for Character Recognition (2000)

Shailesh Kumar, Joydeep Ghosh, Melba Crawford

In this chapter, we develop a Bayesian Pairwise Classier framework that is suitable for pattern recognition problems involving a moderately large number of classes, and apply it to two character...

GAMLS: A Generalized framework for Associative Modular Learning Systems (1999)

Shailesh Kumar, Joydeep Ghosh

Learning a large number of simple local concepts is both faster and easier than learning a single global concept. Inspired by this principle of divide and conquer, a number of modular learning...

Designing Genetic Algorithms for the State Assignment Problem (1999)

José Nelson Amaral, Kagan Tumer, Joydeep Ghosh

Finding the best state assignment for implementing a synchronous sequential circuit is important for reducing silicon area or chip count in many digital designs. This State Assignment Problem (SAP)...

Distance Based Clustering of Association Rules (1999)

Gunjan Gupta, Alexander Strehl, Joydeep Ghosh

N/A

Effective Supra-Classifiers for Knowledge Base Construction (1999)

Kurt D. Bollacker, Joydeep Ghosh, Gustavo De Veciana

In this work, we explore the use of the supra-classier framework in the construction of a classier knowledge base. Previously, we introduced this framework within which labels produced by old...

Distance based clustering of association rules (1999)

Alexander Strehl, Gunjan K. Gupta, Joydeep Ghosh

Abstract — Association rule mining is one of the most important procedures in data mining. In industry applications, often more than 10,000 rules are discovered. To allow manual insepection and...

Distance based clustering of association rules (1999)

Gunjan K. Gupta, Alexander Strehl, Joydeep Ghosh

Association rule mining is one of the most important procedures in data mining. In industry applications, often more than 10,000 rules are discovered. To allow manual insepection and support...

Symbolic interpretation of artificial neural networks (1999)

Ismail A. Taha, Joydeep Ghosh

Abstract—Hybrid Intelligent Systems that combine knowledge-based and artificial neural network systems typically have four phases involving domain knowledge representation, mapping of this...

Distance based clustering of association rules (1999)

Gunjan K. Gupta, Alexander Strehl, Joydeep Ghosh

Association rule mining is one of the most important procedures in data mining. In industry applications, often more than 10,000 rules are discovered. To allow manual insepection and support...

Linear and Order Statistics Combiners for Pattern Classification (1999)

A Supra-Classifier Architecture for Scalable Knowledge Reuse (1998)

Several researchers have experimentally shown that substantial improvements can be obtained in difficult pattern recognition problems by combining or integrating the outputs of multiple classifiers....

Ensembles of Radial Basis Function Networks for Spectroscopic Detection of Cervical Pre-Cancer (1998)

When faced with inadequate information, humans often use knowledge gained from previous experience to help them in making decisions. Even when this knowledge is spread thinly among many previous...

Kagan Tumer, Nirmala Ramanujam, Joydeep Ghosh, Rebecca Richards-Kortum

The mortality related to cervical cancer can be substantially reduced through early detection and treatment. However, current detection techniques, such as Pap smear and colposcopy, fail to achieve a...

On the Use of Localized Gating in Mixture of Experts Networks (1998)

Classifier Combining through Trimmed Means and Order Statistics (1998)

The "mixture-of-experts (MOE)" is a popular architecture for function approximation. In the standard architecture, each expert is gated via a softmax function, and its domain of application...

A Flexible Resource Allocating Network for Noisy Data (1998)

Combining the outputs of multiple neural networks has led to substantial improvements in several difficult pattern recognition problems. In this article, we introduce and investigate robust...

Arindam Nag, Joydeep Ghosh

The resource allocating network(RAN) provides a simple and powerful method for on-line modeling with incremental growth in model complexity. However, the network growing algorithm is susceptible to...

A Mutual Information Based Ensemble Method To Estimate Bayes Error (1998)

Kagan Tumer, Kurt Bollacker, Joydeep Ghosh

: Determining the performance bounds possible with a particular classifier or data set is often of great importance in pattern recognition applications. A previously introduced method for Bayes error...

On The Design of Supra-Classifiers for Knowledge Reuse (1998)

Kurt Bollacker, Joydeep Ghosh

We have recently introduced a framework for the reuse of knowledge from previously trained classifiers to improve performance in a current, possibly related classification task. This framework...

Ensembles of radial basis function networks for spectroscopic detection of cervical precancer (1998)

Kagan Tumer, Nirmala Ramanujam, Joydeep Ghosh, Rebecca Richards-kortum

The mortality related to cervical cancer can be substantially reduced through early detection and treatment. However, current detection techniques, such as Pap smear and colposcopy, fail to achieve a...

Spectroscopic Detection of Cervical Pre-Cancer through Radial Basis Function Networks (1997)

Kagan Tumer Kagan, Nirmala Ramanujam, Joydeep Ghosh

The mortality related to cervical cancer can be substantially reduced through early detection and treatment. However, current detection techniques, such as Pap smear and colposcopy, fail to achieve a...

Bayes Error Rate Estimation Using Neural Network Ensembles (1997)

Knowledge Reuse in Multiple Classifier Systems (1997)

Assessing the performance of a given pattern classifier requires knowing the lowest achievable error, or the Bayes error rate. There are several classical approaches for estimating or finding bounds...

Kurt Dewitt, Kurt Dewitt Bollacker, Joydeep Ghosh

We introduce a framework for the reuse of knowledge from previously trained classifiers to improve performance in a current and possibly related classification task. The approach used is flexible in...

Evaluation and Ordering of Rules Extracted from Feedforward Networks (1997)

Function Emulation using Radial Basis Function Networks (1997)

Rules extracted from trained feedforward networks can be used for explanation, validation, and crossreferencing of network output decisions. This paper introduces a rule evaluation and ordering...

A Scalable Method for Classifier Knowledge Reuse (1997)

While learning an unknown input-output task, humans first strive to understand the qualitative structure of the function. Accuracy of performance is then improved with practice. In contrast, existing...

Regularization and Error Bars for the Mixture of Experts Network (1997)

Just as a person's life-long experience helps him/her in new classification tasks, it would be useful to leverage the knowledge in previously trained artificial classifiers in learning future...

A Concurrent Architecture for Serializable Production Systems (1996)

The mixture of experts architecture provides a modular approach to function approximation. Since different experts get attuned to different regions of the input space during the course of training,...

Jos'e Nelson Amaral, Joydeep Ghosh

This paper presents a new production system architecture that takes advantage of modern associative memory devices to allow parallel production firing, concurrent matching, and overlap among...

Flexible modular architecture for changing environments (1996)

Theoretical Foundations Of Linear And Order Statistics Combiners For Neural Pattern Classifiers (1996)

This paper introduces a neural network capable of dynamically adapting its architecture to model a task that can change with time. This network has its roots in the mixture of experts framework....

Estimating the Bayes Error Rate through Classifier Combining (1996)

: Several researchers have experimentally shown that substantial improvements can be obtained in difficult pattern recognition problems by combining or integrating the outputs of multiple...

Error Correlation And Error Reduction In Ensemble Classifiers (1996)

The Bayes error provides the lowest achievable error rate for a given pattern classification problem. There are several classical approaches for estimating or finding bounds for the Bayes error. One...

A Comparative Study of Three Paradigms for Object Recognition - Bayesian Statistics, Neural Networks and Expert Systems. (1996)

Using an ensemble of classifiers, instead of a single classifier, can lead to improved generalization. The gains obtained by combining however, are often affected more by the selection of what is...

J. K. Aggarwal, Joydeep Ghosh, Dinesh Nair, Ismail Taha

Object recognition, which involves the classification of objects into one of many a priori known object types, and determining object characteristics such as pose, is a difficult problem. A wide...

ANALYSIS OF DECISION BOUNDARIES IN LINEARLY COMBINED NEURAL CLASSIFIERS Kagan Tumer and Joydeep Ghosh (1996)

A Concurrent Architecture for Serializable Production Systems (1996)

: Combining or integrating the outputs of several pattern classifiers has led to improved performance in a multitude of applications. This paper provides an analytical framework to quantify the...

Jos'e Nelson, Jos'e Nelson Amaral, Joydeep Ghosh

This paper presents a new production system architecture that takes advantage of modern associative memory devices to allow parallel production firing, concurrent matching, and overlap among...

A Complex-valued Associative Memory for Storing Patterns as Oscillatory States (1996)

Srinivasa Chakravarthy, Joydeep Ghosh

A neuron model in which the neuron state is described by a complex number is proposed. A network of these neurons, which can be used as an associative memory, operates in two distinct modes: (i)...

A Concurrent Architecture for Serializable Production Systems (1996)

Jos'e Nelson Amaral, Joydeep Ghosh

This paper presents a new production system architecture that takes advantage of modern associative memory devices to allow parallel production firing, concurrent matching, and overlap among...

Some Limitations of Linear Memory Architectures for Signal Processing (1996)

Some Limitations of Linear Memory Architectures for Signal Processing (1996)

Certain neural network structures with a linear "memory" stage followed by a nonlinear memoryless stage are commonly used for signal processing. Two examples of such structures are the time...

Symbolic Interpretation of Artificial Neural Networks (1996)

Certain neural network structures with a linear "memory" stage followed by a nonlinear memoryless stage are commonly used for signal processing. Two examples of such structures are the time...

Automatic Generation of Versatile Benchmarks for Parallel Production System Architectures (1996)

Hybrid Intelligent Systems that combine knowledge based and artificial neural network systems typically have four phases involving domain knowledge representation, mapping of this knowledge into an...

Jose Nelson Amaral, Joydeep Ghosh

The shortage of adequate benchmarking facilities is a major problem in the proper evaluation of production system machine organizations. This paper presents a new benchmark problem that allows...

Mutual Information Feature Extractors for Neural Classifiers (1996)

Linear Feature Extractors Based on Mutual Information (1996)

This paper presents and evaluates two linear feature extractors based on mutual information. These feature extractors consider general dependencies between features and class labels, as opposed to...

Scale-based Clustering using the Radial Basis Function Network (1996)

This paper presents and evaluates two linear feature extractors based on mutual information. These feature extractors consider general dependencies between features and class labels, as opposed to...

Rinivasa V. Chakravarthy, Joydeep Ghosh

This paper shows how scale-based clustering can be done using the Radial Basis Function (RBF) Network, with the RBF width as the scale parameter and a dummy target as the desired output. The...

Three Techniques for Extracting Rules from Feedforward Networks (1996)

Structural Adaptation in Mixture of Experts (1996)

Hybrid intelligent systems that combine knowledge based and artificial neural network systems typically have four phases involving domain knowledge representation, mapping into connectionist network,...

Symbolic Interpretation of Artificial Neural Networks (1996)

The "mixture of experts" framework provides a modular and flexible approach to function approximation. However, the important problem of determining the appropriate number and complexity of...

On Hebbian-like Adaptation in Heart Muscle: A Proposal for "Cardiac Memory" (1996)

Hybrid Intelligent Systems that combine knowledge based and artificial neural network systems typically have four phases involving domain knowledge representation, mapping of this knowledge into an...

Characterization of the Wisconsin Breast cancer Database Using a Hybrid Symbolic-Connectionist System (1996)

Studies on the effects of external pacing of heart suggest that the organ, like the nervous system, possesses the properties of "memory" and adaptation [RBE + 82]. Changes induced in...

Advances In Using Hierarchical Mixture Of Experts For Signal Classification (1996)

E xtracting rules from trained artificial neural networks adds more powerful features to their output decisions. The explanation, validation, and cross-referencing are some of these powerful...

Scale-based Clustering using the Radial Basis Function Network (1996)

The Hierarchical mixture of experts(HME) architecture is a powerful tree structured architecture for supervised learning. In this paper, an efficient one-pass algorithm to solve the M-step of the EM...

Error correlation and error reduction in ensemble classifiers (1996)

Adaptive learning dynamics of the Radial Basis Function Network (RBFN) are compared with a scale-based clustering technique [Won93] and a relationship between the two is pointed out. Using this link,...

Analysis of decision boundaries in linearly combined neural classifiers (1996)

bootstrapping, resampling. Using an ensemble of classifiers, instead of a single classifier, can lead to improved generalization. The gains obtained by combining however, are often affected more by...

A Concurrent Architecture for Serializable Production Systems (1996)

Abstract: Combining or integrating the outputs of several pattern classifiers has led to improved performance in a multitude of applications. This paper provides an analytical framework to quantify...

Jose Nelson Amaral, Joydeep Ghosh

Abstract-This paper presents a new production system architecture that takes advantage of modern associative memory devices to allow parallel production firing, concurrent matching, and overlap among...

Predictive Dynamic Bandwidth Allocation for Efficient Transport of Real-Time VBR Video over ATM (1995)

Chong, Song, Li, San-qi, Ghosh, Joydeep

This paper presents a novel approach to dynamic transmission bandwidth allocation for transport of real-time variable-bit-rate video in ATM networks. Video traffic statistics are measured in the...

Designing genetic algorithms for the state assignment problem (1995)

José Nelson Amaral, Kagan Tumer, Joydeep Ghosh

Abstract — Finding the best state assignment for implementing a synchronous sequential circuit is important for reducing silicon area or chip count in many digital designs. This State Assignment...

A Hybrid Intelligent Architecture for Refining Input Characterization and Domain Knowledge (1995)

Boundary Variance Reduction for Improved Classification through Hybrid Networks (1995)

: A Hybrid Intelligent Architecture that aims to exploit the complementary features of expert systems and connectionist architecture, is proposed to revise input characterization and initial domain...

Boundary Variance Reduction for Improved Classification through Hybrid Networks (1995)

Several researchers have experimentally shown that substantial improvements can be obtained in difficult pattern recognition problems by combining or integrating the outputs of multiple classifiers....

A Habituation Based Mechanism for Encoding Temporal Information in Artificial Neural Networks (1995)

Several researchers have experimentally shown that substantial improvements can be obtained in difficult pattern recognition problems by combining or integrating the outputs of multiple classifiers....

Habituation Based Neural Networks for Spatio-Temporal Classification (1995)

A novel neural network is proposed for the dynamic classification of spatio-temporal signals. The network is designed to classify signals of different durations, taking into account correlations...

A Habituation Based Neural Network for Spatio-Temporal Classification (1995)

A new class of neural networks are proposed for the dynamic classification of spatio-temporal signals. These networks are designed to classify signals of different durations, taking into account...

Habituation Based Neural Classifiers For Spatio-Temporal Signals (1995)

A novel neural network is proposed for the dynamic classification of spatio-temporal signals. The network is designed to classify signals of different durations, taking into account correlations...

Bryan Stiles, Joydeep Ghosh

Based on the habituation mechanism found in biological neural systems, novel dynamic neural networks are proposed for recognizing temporal patterns. The specific task considered in this paper is the...

Efficient Higher-order Neural Networks for Classification and Function Approximation (1995)

Joydeep Ghosh, Yoan Shin

This paper introduces a class of higher-order networks called pi-sigma networks (PSNs). PSNs are feedforward networks with a single "hidden" layer of linear summing units, and with product...

Versatile Benchmarking for Concurrent Production System Architectures (1995)

Jos'e Nelsonn Amaral, Joydeep Ghosh

The shortage of adequate benchmarking facilities is a major problem in the evaluation of novel production system machine organizations. This paper presents a survey of benchmark programs used in...

A Habituation Based Neural Network for Spatio-Temporal Classification (1995)

Using Queueing Theory for Analytical Performance Evaluation of a Multiple Functional Unit Rete Network (1995)

A novel neural network is proposed for the dynamic classification of spatio-temporal signals. The network is designed to classify signals of different durations, taking into account correlations...

Associative Memories Provide an Efficient Control Mechanism for a Parallel Production System Architecture (1995)

The matching phase is believed to require as much as 90 percent of the execution time of a production system. The Rete Network is the most well known and broadly used matching algorithm for...

Integration Of Neural Classifiers For Passive Sonar Signals (1995)

Recently we proposed a parallel architecture for production systems [2, 3, 5]. This novel architecture allows parallel production firing, concurrent matching, and overlap among matching, selection,...

Joydeep Ghosh, Kagan Tumer, Steven Beck, Larry Deuser

The identification and classification of underwater acoustic signals is an extremely difficult problem because of low SNRs and a high degree of variability in the signals emanated from the same type...

Classifier Combining: Analytical Results and Implications (1995)

Predictive Dynamic Bandwidth Allocation for Efficient Transport of Real-Time VBR Video over ATM (1995)

Several researchers have experimentally shown that substantial improvements can be obtained in difficult pattern recognition problems by combining or integrating the outputs of multiple classifiers....

On Hebbian-like Adaptation in Heart Muscle: A Proposal for "Cardiac Memory" (1995)

This paper presents a novel approach to dynamic transmission bandwidth allocation for transport of real-time variable-bit-rate video in ATM networks. Video traffic statistics are measured in the...

Srinivasa Chakravarthy, Joydeep Ghosh

Studies on the effects of external pacing of heart suggest that the organ, like the nervous system, possesses the properties of "memory" and adaptation [RBE + 82]. Changes induced in...

A Hybrid Intelligent Architecture and Its Application to Water Reservoir Control (1995)

Controlling Water Reservoirs Using A Hybrid Intelligent Architecture (1995)

Measured inputs in control domains are often continuous. A discretization function is needed to map continuous inputs into multiple intervals or ranges of input values, so that they can be used as...

Classification Of Spatio-Temporal Patterns With Applications To Recognition Of Sonar Sequences (1995)

: Measured inputs in control domains are often continuous. A discretization function is needed to map continuous inputs into multiple intervals or ranges of input values, so that they can be used as...

Joydeep Ghosh, Larry Deuser

this article, the wavelet transform is used to generate sixteen coefficients that describe the spectral characteristics of the signal. These sixteen coefficients are augmented with temporal...

Order Statistics Combiners For Neural Classifiers (1995)

Performance Measurements of a Concurrent Production System Architecture without Global Synchronization (1995)

: Several researchers have shown that linearly combining outputs of multiple neural classifiers results in better performance for many applications. In this paper we introduce a family of order...

Jose Nelson Amaral, Joydeep Ghosh, Amaral Joydeep Ghosh

The use of the serializability criterion of correctness allows the elimination of global synchronization in production system machines. In this paper we present an extensive performance evaluation of...

A Network Of Oscillating Neurons For Image Segmentation (1995)

Srinivasa V. Chakravarthy, Viswanath Ramamurti, Joydeep Ghosh

: We propose a neural network of complex-valued neurons that exhibits stimulus-specific oscillations. Synchronization of oscillations is produced by either of two mechanisms: (i) co-operation among...

Dynamic Bandwidth Allocation for Efficient Transport of Real-Time VBR Video over ATM (1994)

Chong, Song, Li, San-qi, Ghosh, Joydeep

The paper presents a novel approach to dynamic transmission bandwidth allocation for transport of real-time variable-bit-rate video in ATM networks. The authors describe video traffic in the...

A Framework For Estimating Performance Improvements In Hybrid Pattern Classifiers (1994)

Distributed Control Schemes for Fast Arbitration in Large Crossbar Networks (1994)

: Classification methods often perform significantly below Bayesian limits in complex, high-dimensional classification tasks because of model bias, inadequate training data and noise/variability in...

Joydeep Ghosh, Naveen Krishnamurthy, Anujan Varma

In a large nonblocking crossbar switch, the controller often becomes a bottleneck in terms of both performance and reliability. In this paper, we present a number of schemes for distributing the...

An Associative Memory Architecture for Concurrent Production Systems (1994)

Jose Nelson Amaral, Joydeep Ghosh

This paper presents a novel parallel architecture for production systems. It relies on modern associative memory techniques to construct an environment in which productions can be fired in parallel...

Repeated Computation of Global Functions in a Distributed Environment (1994)

Vijay K. Garg, Joydeep Ghosh

In a distributed system, many algorithms need repeated computation of a global function. These algorithms generally use a static hierarchy for gathering necessary data from all processes. As a...

Dynamic Bandwidth Allocation for Efficient Transport of Real-Time VBR Video over ATM (1994)

An Associative Memory Architecture for Concurrent Production Systems (1994)

This paper 1 presents a novel approach to dynamic transmission bandwidth allocation for transport of real-time variable-bit-rate video in ATM networks. Describe video traffic in the frequency domain:...

Jos'e Nelson, Jos'e Nelson Amaral, Joydeep Ghosh

This paper presents a novel parallel architecture for production systems. It relies on modern associative memory techniques to construct an environment in which productions can be fired in parallel...

A Neural Network-based Associative Memory for Storing Complex-valued Patterns (1994)

Vision Based Inspection (1994)

A neural network-based associative memory for storing complex patterns is proposed. Two variations of the model are proposed: (1) discrete model and, (2) continuous model. The latter approaches the...

Joydeep Ghosh

INTRODUCTION In industrial manufacturing, product inspection is an important step in the production process. Since product reliability and quality management is of utmost importance in most...

A Comprehensive Analytical Model for Wormhole Routing in Multicomputer Systems (1994)

Jeffrey T. Draper, Joydeep Ghosh

An analytical model for obtaining performance measures in multicomputer networks which use wormhole routing is presented. Unlike previous wormhole routing models, the model introduced in this paper...

Repeated computation of global functions in a distributed environment (1994)

Vijay K. Garg, Joydeep Ghosh

Abstract- In a distributed system, many algorithms need repeated computation of a global function. These algorithms generally use a static hierarchy for gathering necessary data from all processes....

A Macroscopic Model of Oscillation in Ensembles of Inhibitory and Excitatory Neurons (1993)

Joydeep Ghosh, Hung-jen Chang, Kadir Liano

Very large networks of neurons can be characterized in a tractable and meaningful way by considering the average or ensemble behavior of groups of cells. This paper develops a mathematical model to...

Concurrent Procesing of Linearly Ordered Data Structures on Hypercube Multicomputers (1993)

Joydeep Ghosh, Sajal Das, Ajita John, T. A. Ottomann, A. L. Rosenberg, Ieee Trans Comput, ...

This paper presents a simple and effective method for the concurrent manipulation of linearly ordered data structures on hypercube systems. The method is based on the existence of an augmented...

Robust Classification of Variable Length Sonar Sequences (1993)

Joydeep Ghosh, Narsimham V. Gangishetti, Srinivasa V. Chakravarthy

. Two types of artificial neural networks are introduced for the robust classification of spatio-temporal sequences. The first network is the Adaptive Spatio-Temporal Recognizer (ASTER), which...

A Temporal Memory Network with State-dependent Thresholds (1993)

Joydeep Ghosh, Shaoyun Wang

A fully connected recurrent network that is capable of storing, recalling, and generating a pattern sequence, is presented. This network reproduces a memorized sequence by synchronous updating, and...

Fault-Tolerant Arbitration in Multichip Crossbar Switches (1993)

Joydeep Ghosh, N. Krishnamurthy

. A major problem in the design of large multichip crossbar networks is the latency associated with the centralized controller used to arbitrate requests. We present a solution to reduce this latency...

Performance Evaluation of a Parallel I/O Subsystem for Hypercube Multicomputers (1993)

Hypercube Multicomputers, Kelvin D. Goveas, Jeffrey T. Draper, Joydeep Ghosh, Joydeep Ghosh

Though input/output (I/O) from mass storage continues to be a bottleneck in current generation distributed-memory multicomputers, few studies have been conducted on the system-level impact of an...

Applying Genetic Algorithms to the State Assignment Problem: A case Study (1992)

Jose Nelson, Jose Nelson Amaral, Kagan Tumer, Joydeep Ghosh

Finding the best state assignment for implementing a synchronous sequential circuit is important for reducing silicon area or chip count in many digital designs. This State Assignment Problem (SAP)...

Evidence Combination Techniques For Robust Classification Of Short-Duration Oceanic Signals (1992)

Joydeep Ghosh, Steven Beck, Chen-chau Chu

. The identification and classification of underwater acoustic signals is an extremely difficult problem because of low SNRs and a high degree of variability in the signals emanated from the same...

Multipath E-Cube Algorithms (MECA) for Adaptive Wormhole Routing and Broadcasting in (1992)

Ary Cubes, Jeffrey T. Draper, Joydeep Ghosh

This paper introduces and evaluates the Multipath E-Cube Algorithm (MECA) for adaptive and faulttolerant wormhole routing in k-ary n-cubes. This algorithm provides multiple shortest paths between any...

Approximation of Multivariate Functions Using Ridge Polynomial Networks (1992)

Pattern Association and Retrieval in a Continuous Neural System (1992)

In this paper, a new class of higher-order feedforward neural networks, called ridge polynomial networks (RPN) is formulated. The new networks are shown to uniformly approximate any continuous...

Hung-jen Chang, Joydeep Ghosh

This paper studies the behavior of a large body of neurons in the continuum limit. A mathematical characterization of such systems is obtained by approximating the inverse input-output nonlinearity...

Computationally Efficient Invariant Pattern Recognition With Higher Order Pi-Sigma Networks (1992)

A Neural Network Based Hybrid System for Detection, Characterization and Classification of Short-Duration Oceanic Signals (1992)

A class of higher-order networks called Pi-Sigma networks has recently been introduced for function approximation and classification [4]. These networks combine the fast training abilities of...

Joydeep Ghosh, Larry Deuser, Steven Beck

Automated identification and classification of short-duration oceanic signals obtained from passive sonar is a complex problem because of the large variability in both temporal and spectral...

Multipath E-Cube Algorithms (MECA) for Adaptive Wormhole Routing and Broadcasting in (1992)

Ary Cubes, Jeffrey T. Draper, Joydeep Ghosh

This paper introduces and evaluates the Multipath E-Cube Algorithm (MECA) for adaptive and faulttolerant wormhole routing in k-ary n-cubes. This algorithm provides multiple shortest paths between any...

The M-Cache: A Message-Retrieving Mechanism for Multicomputer Systems (1991)

Jeffrey Draper, Joydeep Ghosh, William C. Athas

This paper presents the design and evaluation of the M-cache, a small, fast and intelligent memory for handling messages at the processing nodes of multicomputer systems. The M-cache provides...

Neural Networks for Fast Arbitration and Switching Noise Reduction in Large Crossbars (1991)

Joydeep Ghosh, Member Ieee, Anujan Varma, Ajat Hukkoo, Student Member

A neural network-based controller is presented for the real-time arbitration of routing paths in large crossbar switches constructed from one-sided crosspoint chips. This controller is suitable for a...

Realization of Boolean Functions Using Binary Pi-sigma Networks (1991)

A Macroscopic Model of Neural Ensembles I: Learning-Induced Oscillations in a Cell Assembly (1991)

This paper introduces a higher-order neural network called the Binary Pi-sigma Network (BPSN), which is a feedforward network with a single "hidden" layer and product units in the output...

Hung-jen Chang, Joydeep Ghosh, Kadir Liano

A mathematical model is developed to characterize the aggregate behavior of large neural networks in which each individual neuron can be described by the general Hodgkin-Huxley format. Equations...

A Macroscopic Model of Neural Ensembles I: Learning-Induced Oscillations in a Cell Assembly (1991)

Hung-jen Chang, Joydeep Ghosh, Kadir Liano

A mathematical model is developed to characterize the aggregate behavior of large neural networks in which each individual neuron can be described by the general Hodgkin-Huxley format. Equations...

The M-Cache: A Message-Retrieving Mechanism for Multicomputer Systems (1991)

Jeffrey Draper, Joydeep Ghosh, William C. Athas

This paper presents the design and evaluation of the M-cache, a small, fast and intelligent memory for handling messages at the processing nodes of multicomputer systems. The M-cache provides...

The Pi-sigma Network : An Efficient Higher-Order Neural Network for Pattern Classification and Function Approximation (1991)

Adaptive Kernel Classifiers for Short-Duration Oceanic Signals (1991)

This paper introduces a novel feedforward network called the pi-sigma network. This network utilizes product cells as the output units to indirectly incorporate the capabilities of higher-order...

Joydeep Ghosh, Srinivasa Chakravarthy, Yoan Shin, Chen-Chau Chu, Larry Deuser, Steven Beck, ...

Two kernel networks are presented for the classification of short-duration acoustic signals characterized by wavelet coefficients and signal duration. These networks combine the positive features of...

Specialization: Microprocessor Systems WORK EXPERIENCE (1991)

Jeffrey T. Draper, Supervising Professors, Dr. William Athas, Dr. Joydeep Ghosh, Southern California

Directed VLSI efforts of several DARPA-funded projects. Contributed to the architecture design of polymorphous computing architectures and co-led the VLSI implementation of a representative chip in...

Textured Image Segmentation Using Localized Receptive Fields (1990)

Joydeep Ghosh, Nanda Gopal, A Gopal, Alan C. Bovik

: We present an approach to texture analysis that uses spatially localized filters and cooperativecompetitive mechanisms for determining emergent boundaries. Gabor filters that closely resemble...

Mapping Neural Networks onto Message-Passing Multicomputers (1989)

Message-passing Multicomputers, Joydeep Ghosh, Kai Hwang

This paper investigates the architectural requirements for simulating neural networks using massively parallel multiprocessors. First, we model the connectivity patterns in large neural networks. A...

Optically Connected Multiprocessors for Simulating Artificial Neural Networks (1988)

Joydeep Ghosh, Kai Hwang

This paper investigates the architectural requirements in simulating large neural networks using a highly parallel multiprocessor with distributed memory and optical interconnects. First, we model...

Communications-efficient architectures for massively parallel processing : by Joydeep Ghosh. (1988)

Ghosh, Joydeep.

Thesis (Ph. D.)--University of Southern California, 1988.

Limits To Performance Gains In Combined Neural Classifiers

Kagan Tumer And, Kagan Tumer, Joydeep Ghosh

: The performance of a single classifier is often inadequate in difficult classification problems. In such cases, several researchers have combined the outputs of multiple classifiers to obtain...

Structurally Adaptive Modular Networks for Non-Stationary Environments