CARMEN: an e-science virtual laboratory supporting collaboration in neuroinformatics (2009)
Ingram, Colin D, Watson, Paul, Austin, Jim, Smith, Leslie S
No abstract available.
Abstract Designing a Binary Neural Network Co-processor (2008)
A Correlation Matrix Memory (CMM) is a form of binary neural network, that can be used for high-speed approximate search and match operations on large unstructured datasets. Typically, the processing...
Flexible Dynamic Binding in Agile Grid Development 1 (2008)
Jovan Cakic, Richard F. Paige, Howard Chivers, Xiaocheng Ge, John A. Mcdermid, Jim Austin
The eXGrid project focuses on the agile development of Grids, in order to more flexibly build dynamic virtual organizations. A key issue in supporting virtual organizations in Grids is a more...
Pattern Matching Against Distributed Datasets (2008)
Mark Jessop, Andy Pasley, Jim Austin
Aero-engine vibration and performance data is downloaded each time an aircraft lands. On a fleet wide basis this process soon generates terabyte scale datasets. Given the large volume of data and the...
Eliciting Perceptual Ground Truth for Image Segmentation. (2008)
Victoria Hodge, John Eakins, Jim Austin
In this paper, we investigate human visual perception and establish a body of ground truth data elicited from human visual studies. We aim to build on the formative work of Ren, Eakins and Briggs who...
2003) Distribution forecasting of high frequency time series, Decision Support Systems (2008)
The availability of high frequency data sets in finance has allowed the use of very data intensive techniques using large data sets in forecasting. An algorithm requiring fast k-NN type search has...
Systems. This paper has been peer-reviewed but does not include the final publisher proof-corrections or journal pagination. White Rose Repository URL for this paper:
Eliciting Perceptual Ground Truth for Image Segmentation. (2008)
Victoria Hodge, Garry Hollier, John Eakins, Jim Austin
In this paper, we investigate human visual perception and establish a body of ground truth data elicited from human visual studies. We aim to build on the formative work of Ren, Eakins and Briggs who...
A Binary Neural Decision Table Classifier (2008)
In this paper, we introduce a neural network-based decision table algorithm. We focus on the implementation details of the decision table algorithm when it is constructed using the neural network....
Abstract. K-Nearest Neighbour (k-NN) is a widely used technique for classifying and clustering data. k-NN is effective but is often criticised for its polynomial run-time growth as k-NN calculates...
Cellular Associative Neural Networks (CANN) (2008)
Grant Brewer, Stefan Klinger, Jim Austin
We propose to present a novel syntactic pattern matching technique [1] that combines the correlative learning and generalisation properties of associative memories, with the parallel and distributed...
Chemical Similarity Searching Using a Neural Graph Matcher (2008)
Abstract. A neural graph matcher based on Correlation Matrix Memories is evaluated in terms of efficiency and effectiveness against two maximum common subgraph (mcs) algorithms. The algorithm removes...
Safety Criteria and Safety Lifecycle for Artificial Neural Networks (2008)
Zeshan Kurd, Tim Kelly, Jim Austin
ABSTRACT: There are many performance based techniques that aim to improve the safety of neural networks for safety critical applications. However, many of these techniques provide inadequate forms of...
The Distributed Aircraft Maintenance (2008)
Tom Jackson, Jim Austin, Martyn Fletcher, Mark Jessop
We provide an overview of the DAME project, and a discussion of the progress made to date on the development of a distributed aeroengine diagnosis environment as a proof of concept demonstration for...
Pattern Matching in DAME using Grid Enabled AURA Technology (2008)
Robert Davis, Bojian Liang, Mark Jessop, Andy Pasley, Jim Austin
This paper describes research on the DAME Project into the use of Correlation Matrix Memories for imprecise pattern matching on large volumes of time series data using the Grid. This technology,...
Fletcher, Martyn, Liang, Bojian, Smith, Leslie S., Kownles, Alastair, Jackson, Tom, Jessop, Mark, ...
In the study of information flow in the brain, component processes can be investigated using a range of electrophysiological and imaging techniques. Although data is difficult and expensive to...
Spiking Correlation Matrix Memory (2007)
This paper looks at construction of CMMs as purely spiking entities.
VLSI implementation of a Binary Neural Networktwo case studies (2007)
A comparison between a bit-level and a conventional VLSI implementation of a binary neural network is presented. This network is based on Correlation Matrix Memory (CMM) that stores relationships...
Stefan Wermter, Jim Austin, David Willshaw
Council (EPSRC). The overall aim of the book is to present a broad spectrum of current research into biologically inspired computational systems and hence encourage the emergence of new computational...
Layout indexing of trademark images (2007)
Ensuring the uniqueness of trademark images and protecting their identities are the most important objectives for the trademark registration process. To prevent trademark infringement, each new...
List of Potential Supervisors (2007)
Neil Audsley, Jim Austin, Iain Bate, Ian Benest, Sam Braunstein, Alan Burns, ...
This document outlines some of the present research interests of most members of the Department who are in a position to supervise the research of students entering in October 2007. The sections are...
A Binary Neural Shape Matcher using Johnson Counters and Chain Codes (2006)
Hodge, Victoria, O'Keefe, Simon, Austin, Jim
In this paper, we introduce a neural network-based shape matching algorithm that uses Johnson Counter codes coupled with chain codes. Shape matching is a fundamental requirement in content-based...
Chemical similarity searching forms an important part of the virtual screening process. In this study, we present a graph-based matching method that assembles the target query graph from a number of...
Michael Weeks, Michael Freeman, Anthony Moulds, Jim Austin
The AICP (Ambient Intelligent Co-Processor) project aims are to develop and implement high performance hardware pattern matching algorithms for use in embedded ubiquitous systems. As part of this...
Hardware implementation of Similarity Functions (2005)
Michael Freeman, Michael Weeks, Jim Austin
A number of applications varying from music to document classification, require the similarity between a collection of objects to be calculated. To achieve this, features about these objects are...
A survey of outlier detection methodologies (2004)
Abstract. Outlier detection has been used for centuries to detect and, where appropriate, remove anomalous observations from data. Outliers arise due to mechanical faults, changes in system...
Three-Dimensional Face Recognition Using Surface Space Combinations (2004)
Thomas Heseltine, Nick Pears, Jim Austin
In this paper we test a range of three-dimensional face recognition systems, based on the fishersurface method developed in previous work. We show the effect of using a variety of facial surface...
Three-Dimensional Face Recognition: A Fishersurface (2004)
Approach Thomas Heseltine, Thomas Heseltine, Nick Pears, Jim Austin
Previous work has shown that principal component analysis (PCA) of three-dimensional face models can be used to perform recognition to a high degree of accuracy. However, experimentation with...
Exploiting Safety Constraints in Fuzzy Self-Organising Maps for Safety Critical Applications (2004)
Zeshan Kurd, Tim P. Kelly, Jim Austin
Abstract. This paper defines a constrained Artificial Neural Network (ANN) that can be employed for highly-dependable roles in safety critical applications. The derived model is based upon the Fuzzy...
A survey of outlier detection methodologies (2004)
This paper has been peer-reviewed but does not include the final publisher proof-corrections or journal pagination. White Rose Repository URL for this paper:
Z.: Face Recognition: A Comparison of Appearance-Based Approaches (2003)
Thomas Heseltine, Nick Pears, Jim Austin, Zezhi Chen
Abstract. We investigate the effect of image processing techniques when applied as a pre-processing step to three methods of face recognition: the direct correlation method, the eigenface method and...
Whither Social Initiatives by Business? (2001)
Joshua D. Margolis, James P. Walsh, Howard Aldrich, Alan Andreasen, Jim Austin, Charles Behling, ...
Corporations have responded to society’s plea to provide innovative solutions to deep-seated problems of human misery. Organization and management scholarship can play an important role in...
An Evaluation of Phonetic Spell Checkers (2001)
Victoria J. Hodge, Jim Austin, Yo Dd, Yo Dd
In the work reported here, we describe a phonetic spell-checking algorithm, Phonetex which integrates aspects of Soundex and its extension Phonix. It is designed to provide a phonetic component for...
the EmerNet project on Emergent Neural Computational Architectures based (2001)
Stefan Wermter, Jim Austin, David Willshaw
Council (EPSRC). The overall aim of the book is to present a broad spectrum of current research into biologically inspired computational systems and hence encourage the emergence of new computational...
An Integrated Neural IR System (2001)
Abstract. Over the years the amount and range of electronic text stored on the WWW has expanded rapidly, overwhelming both users and tools designed to index and search the information. It is...
Hierarchical growing cell structures: TreeGCS (2000)
We propose a hierarchical, unsupervised clustering algorithm (TreeGCS) based upon the Growing Cell Structure (GCS) neural network of Fritzke. Our algorithm improves an inconsistency in the GCS...
An Evaluation of Standard Retrieval Algorithms and a Weightless Neural Approach (2000)
Many computational processes require efficient algorithms, those that both store and retrieve data efficiently and rapidly. In this paper we evaluate a selection of data structures for storage...
Trademark image retrieval using multiple features (1999)
This paper describes an ongoing research project aimed at implementing a trademark retrieval system using an associative memory neural network. The novel aspect presented in this paper is the...
A PCI Bus Based Correlation Matrix Memory and Its Application to k-NN Classification (1999)
This paper describes a PCI bus based implementation of a binary correlation matrix memory (CMM) neural network and its application and performance for use as a k-NN based pattern classification...
A High-Performance Binary Neural Processor for PCI and VME Bus-based Systems (1999)
Anthony Moulds, Richard Pack, Zygmunt Ulanowski, Jim Austin, Yo Dd
. This paper describes the construction of a high-performance neural processor using fast Sum-And-Threshold logic and Correlation Matrix Memory binary neural network components. The addition of...
A High Performance k-NN Classifier Using a Binary Correlation Matrix Memory (1999)
Ping Zhou, Jim Austin, John Kennedy
This paper presents a novel and fast k-NN classifier that is based on a binary CMM (Correlation Matrix Memory) neural network. A robust encoding method is developed to meet CMM input requirements. A...
A Novel Architecture for Trademark Image Retrieval Systems (1998)
This paper describes the first phase of an ongoing research project aimed at implementing a trademark retrieval system using an associative memory neural network. The novel aspect of the work...
A binary correlation matrix memory k-nn classifier with hardware implementation (1998)
Ping Zhou, Jim Austin, John Kennedy
This paper describes a generic and fast classifier that uses a binary CMM (Correlation Matrix Memory) neural network for storing and matching a large amount of patterns efficiently, and a k-NN rule...
A Parallel Architecture for Binary Neural Networks (1997)
This paper introduces a novel architecture, PRESENCE, which is a hardware implementation of a binary neural network. The architecture described provides two orders of magnitude of speed-up over a...
Theoretical Partial and Multiple Match Performance of CMMs (1997)
We develop a framework for estimating the matching performance of binary correlation matrix memories (CMMs). The framework is applicable to non-recursive, fully-connected systems with binary (0,1)...
Application Of Correlation Memory Matrices In High Frequency Asset Allocation (1997)
Daniel Kustrin, Jim Austin, Alan Sanders, J Austin
Tactical asset allocation is one of the most important aspects of modern financial management. This paper looks at a forecasting architecture that can be used for performing asset allocation with...
A Neural Relaxation Technique For Chemical Graph Matching (1997)
We develop a binary relaxation scheme for graph matching in chemical databases. The technique works by iteratively pruning the list of matching possibilities for individual atoms based upon...
Mathematical Foundation of Statistical Parallelism (1997)
: Statistical Parallelism (SP), is new efficient method of parallel recalling from correlation matrix memories (CMMs). In this paper, we shall first provide a matrix-algebraic base for SP, and then...
High Speed Image Segmentation using a Binary Neural Network. (1996)
In the very near future large amounts of Remotely Sensed data will become available on a daily basis. Unfortunately, it is not clear if the processing methods are available to deal with this data in...
The Cellular Neural Network Associative Processor, C-NNAP (1996)
Jim Austin, Stephen Buckle, John Kennedy, Anthony Moulds, Rick Pack, Aaron Turner, ...
. This paper describes a novel associative processor that uses neural associative memories as its processing elements. The machine has been designed to tackle problems in AI and computer vision,...
The cellular neural network associative processor, C-NNAP (1995)
Jim Austin, Martin Brown, Stephen Buckle, Anthony Moulds, Rick Pack, Aaron Turner, ...
1. Please send any correspondence to this author. 1 This paper describes a novel associative processor that uses neural associative memories as its processing elements. The machine has been designed...
C-NNAP: An Architecture for the Parallel Processing of Binary Neural Networks (1995)
John V. Kennedy, Jim Austin, Rick Pack, Bruce Cass
This paper describes the C-NNAP machine, a MIMD implementation of an array of ADAM binary neural networks, primarily designed for image processing. C-NNAP comprises an array of VME cards each...
The Cellular Neural Network Associative Processor, C-NNAP. (1995)
Jim Austin, Martin Brown, Stephen Buckle, Anthony Moulds, Rick Pack, Aaron Turner, ...
This paper describes a novel associative processor that uses neural associative memories as its processing elements. The machine has been designed to tackle problems in AI and computer vision and...
Image Labelling using an Associative Memory (1995)
Simon O'Keefe, Jim Austin, James Austin
This paper presents an application of an associative memory neural network to the complex task of labelling the parts of an image. The network identifies features in the image, and recalls...
The Advanced Uncertain Reasoning Architecture, AURA (1995)
Jim Austin, John Kennedy, Ken Lees
The ADAM binary neural network which has been used for image analysis applications, is contructed around a central component termed a Correlation Matrix Memory (CMM). A recent reexamination of the...
Segmentation and Matching in infra-red airborne images using a binary neural network. (1995)
This paper describes the application a binary neural network, the Advanced Distributed Associative Memory (ADAM), to the recognition of features in images. In particular, it describes how infra-red...
C-NNAP: A Parallel Processing Architecture for Binary Neural Networks (1995)
John V. Kennedy, Jim Austin, Rick Pack, Bruce Cass
This paper describes the C-NNAP machine, a MIMD implementation of an array of ADAM binary neural networks, primarily designed for image processing. C-NNAP comprises an array of VME cards each...
Statistical Parallelism (1995)
This paper introduces the concept of statistical parallelism. The aim of which is to improve computational performance by allowing a small amount of error. The method relies on the possibility that...
. The analysis of images taken of the ground from aircraft and satellites is of intense importance. This chapter describes work using the ADAM neural network that was aimed at finding way-points,...
The Practical Application of Binary Neural Networks. (1994)
This paper describes the application of binary neural networks, in particular the Advanced Distributed Associative Memory (ADAM) to the recognition of features in images, in particular it describes...
Thomas Jackson, Mark Jessop, Martyn Fletcher, Jim Austin
Industrial and scientific research activity increasingly involves the geographically distributed utilisation of multiple tools, services and distributed data. Grid and Service Orientated Architecture...
UNIVERSITYOF NEWCASTLE COMPUTING SCIENCE University of Newcastle upon Tyne (1042)
The Carmen, Neuroscience Server, P. Watson, T. Jackson, G. Pitsilis, F. Gibson, ...
Understanding the brain is one of the major scientific challenges. It requires the capability to synthesize a detailed and applicable understanding of the way in which information is encoded,...
Matching Performance of Binary Correlation Matrix Memories
We introduce a theoretical framework for estimating the matching performance of binary correlation matrices acting as hetero-associative memories. The framework is applicable to non-recursive,...