Shreekanth Karvaje, Bharat Ravisekar, Saurav Sahay, Baoli Li, Ernest Garcia, Ashwin Ram
Abstract. We propose a semi-supervised method to extract rule sentences from medical abstracts. Medical rules are sentences that give interesting and nontrivial relationship between medical entities....
Player modeling evaluation for interactive fiction (2009)
Manu Sharma, Manish Mehta, Santiago Ontañón, Ashwin Ram
A growing research community is working towards employing drama management components in story-based games that guide the story towards specific narrative arcs depending on a particular player’s...
Drama Management Evaluation for Interactive Fiction Games (2008)
Manu Sharma, Santiago Ontañón, Manish Mehta, Ashwin Ram
A growing research community is working towards employing drama management components in interactive story-based games. These components gently guide the story towards a narrative arc that improves...
Adapting Associative Classification to Text Categorization (2008)
Baoli Li, Neha Sug, Ernest V. Garcia, Ashwin Ram
Associative classification, which originates from numerical data mining, has been applied to deal with text data recently. Text data is firstly digitalized to database of transactions, and then...
* Correspondence Author. Abstract (2008)
Ying Liu, Venu Dasigi, Brian J. Ciliax, Ashwin Ram, Ray Dingledine, Karin Borges, ...
One of the key challenges of microarray studies is to derive biological insights from the unprecedented quantities of data on gene-expression patterns. Clustering genes by functional keyword...
Saurav Sahay, Baoli Li, Ernest V Garcia, Eugene Agichtein, Ashwin Ram
NLM's Unified Medical Language System (UMLS) is a very large ontology of biomedical and health data. In order to be used effectively for knowledge processing, it needs to be customized to a...
PREVENTING FAILURES BY MINING MAINTENANCE LOGS WITH CASE-BASED REASONING (2008)
Mark Devaney, Ashwin Ram, Enkia Corporation, Hai Qiu, Jay Lee
Abstract: The project integrates work in natural language processing, machine learning, and the semantic web, bringing together these diverse disciplines in a novel way to address a real problem. The...
Abstract AN EXPLICIT REPRESENTATION OF FORGETTING (2008)
A pervasive, yet much ignored, factor in the analysis of processing-failures is the problem of misorganized knowledge. If a system’s knowledge is not indexed or organized correctly, it may make an...
Chapter 21 Learning as Goal-Driven Inference (2008)
Ryszard S. Michalski, Ashwin Ram
A remarkable aspect of human learners is that they are able to apply a great variety of learning strategies in a flexible and goal-oriented manner and to dynamically accommodate the demands of...
Santiago Ontañón, Kinshuk Mishra, Neha Sug, Ashwin Ram
Abstract. Artificial Intelligence techniques have been successfully applied to several computer games. However in some kinds of computer games, like real-time strategy (RTS) games, traditional...
Ashwin Ram, Santiago Ontañón, Manish Mehta
Computer games are an increasingly popular application for Artificial Intelligence (AI) research, and conversely AI is an increasingly popular selling point for commercial games. Although games are...
Christina R. Strong, Manish Mehta, Kinshuk Mishra, Alistair Jones, Ashwin Ram
Natural Language Generation for personality rich characters represents one of the important directions for believable agents research. The typical approach to interactive NLG is to hand-author...
reactive control parameters (2008)
Ashwin Ram, Ronald C. Arkin, Kenneth Moorman, Russell J. Clark
Case-based reactive navigation:
Machine Learning Based Semantic Inference: Experiments and Observations at RTE-3 (2008)
Baoli Li, Joseph Irwin, Ernest V. Garcia, Ashwin Ram
Textual Entailment Recognition is a semantic inference task that is required in many natural language processing (NLP) applications. In this paper, we present our system for the third PASCAL...
Akey element in the solution of reinforcement learning problems is the value function. The purpose of this function is to measure the long-term utility or value of any given state. The function is...
A Theory of Reflective Agent Evolution (2007)
J. William Murdock, Alex Kirlik, Ashwin Ram, Spencer Rugaber
Intelligent agents typically operate in complex, dynamic environments. Such environments require that an agent be able to adapt to meet new demands. One promising strategy for such adaptation is to...
Media Spaces PML: Adding Flexibility to Multimedia Presentations (2007)
Ashwin Ram, Richard Catrambone, Mark J. Guzdial, Colleen M. Kehoe, D. Scott Mccrickard, John T. Stasko
systems, designers typically link content and presentation. A new markup language, Procedural Markup Language (PML), decouples content and presentation. It lets users specify the knowledge...
Integratating Robotic Technologies with JavaBots (2007)
this article is primarily concerned with hardware and software technologies. It is our view that significant strides in robot performance can be made just by combining existing hardware and software...
Invention as an Opportunistic Enterprise (2007)
Marin Simina, Janet Kolodner, Ashwin Ram, Michael Gorman
This paper identifies goal handling processes that begin to account for the kind of processes involved in invention. We identify new kinds of goals with special properties and mechanisms for...
Foundations Of, Ashwin Ram, Eric K. Jones
ion as currently used in AI, Brooks concludes, is "a mechanism for self-delusion" (p. 142). But Brooks also supplies his creatures with all of their abstractions: individual layers extract...
Juan Carlos Santamar'ia, Richard S. Sutton, Ashwin Ram
A key element in the solution of reinforcement learning problems is the value function. The purpose of this function is to measure the long-term utility or value of any given state and it is...
Transfer learning in real-time strategy games using hybrid cbr/rl (2007)
Manu Sharma, Michael Holmes, Juan Santamaria, Arya Irani, Charles Isbell, Ashwin Ram
The goal of transfer learning is to use the knowledge acquired in a set of source tasks to improve performance in a related but previously unseen target task. In this paper, we present a multilayered...
Towards Player Preference Modeling for Drama Management in Interactive Stories (2007)
Manu Sharma, Santiago Ontañón, Christina Strong, Manish Mehta, Ashwin Ram
There is a growing interest in producing story based game experiences that do not follow fixed scripts predefined by the author, but change the experience based on actions performed by the player...
Transfer learning in real-time strategy games using hybrid cbr/rl (2007)
Manu Sharma, Michael Holmes, Juan Santamaria, Arya Irani, Charles Isbell, Ashwin Ram
The goal of transfer learning is to use the knowledge acquired in a set of source tasks to improve performance in a related but previously unseen target task. In this paper, we present a multilayered...
Towards runtime behavior adaptation for embodied characters (2007)
Peng Zang, Manish Mehta, Michael Mateas, Ashwin Ram
Typically, autonomous believable agents are implemented using static, hand-authored reactive behaviors or scripts. This hand-authoring allows designers to craft expressive behavior for characters,...
Towards Player Preference Modeling for Drama Management in Interactive Stories (2007)
Manu Sharma, Santiago Ontañón, Christina Strong, Manish Mehta, Ashwin Ram
There is a growing interest in producing story based game experiences that do not follow fixed scripts predefined by the author, but change the experience based on actions performed by the player...
Ying Liu, Shamkant B. Navathe, Jorge Civera, Venu Dasigi, Ashwin Ram, Brian J. Ciliax, ...
Abstract—Partitioning closely related genes into clusters has become an important element of practically all statistical analyses of microarray data. A number of computer algorithms have been...
TEXT MINING BIOMEDICAL LITERATURE FOR GENOMIC KNOWLEDGE DISCOVERY Approved by: (2005)
Shamkant B. Navathe, Chairman Ray Dingledine, Brian J. Ciliax, Edward Omiecinski, Venu Dasigi, Ashwin Ram
This dissertation is dedicated to my parents.
A. Furcy, Sven Koenig Advisor, Ron Ferguson, Ashok Goel, Robert Holte, Ashwin Ram
I would like to thank my advisor, Sven Koenig, for his help with this research. I thank my committee members for their time and guidance. In particular, it has been a great pleasure to collaborate...
Parallel Garbage Collection without Synchronization Overhead. (2002)
Incremental garbage collection schemes incur substantial overhead which is directly translated as reduced execution efficiency for the user. Parallel garbage collection schemes implemented via...
J. William Murdock, Ashok Goel (advisor, Alex Kirlik, Sven Koenig, Colin Potts, Ashwin Ram, ...
Adaptability is a key characteristic of intelligence. My research explores techniques for enabling software agents to adapt themselves as their functional requirements change incrementally. In the...
Using Cognitive Principles to Design Multimedia Training Environments to Support Learning (1998)
Stasko, John, Catrambone, Richard, Guzdial, Mark, Ram, Ashwin
During this project we examined factors that influence how well people learn from multimedia systems. Our project focused on developing multimedia systems to support human learning, based on...
Modeling Multistrategy Learning as a Deliberative Process of Planning (1998)
In July, we presented work related to the ARL project at two conferences. The first presentation at SCI-98 in Orlando, Florida discussed our use of visualization techniques to develop, refine, and...
Introspective Reasoning Models for Multistrategy Case-Based and Explanation (1998)
On the technical front, we have been working towards using the StatLady system as the starting point for implementing our own ideas. By using StatLady, we can make use of the system's large body of...
PML: Representing Procedural Domains for Multimedia Presentations (1998)
Ram, Ashwin, Catrambone, Richard, Guzdial, Mark, Kehoe, Colleen Mary, McCrickard, D. Scott, Stasko, John T.
A central issue in the development of multimedia systems is the presentation of the information to the user of the system and how to best represent that information to the designer of the system....
Cognitive Media and Hypermedia Learning Environment Design: A GOMS Model Analysis (1998)
Terry Shikano, Mimi M. Recker, Ashwin Ram
Abstract. In our research, we have been developing a design framework for educational multimedia, based on the cognitive aspects of the users of that information. Design based on "cognitive...
Needles in a Haystack: Plan Recognition in Large Spatial Domains Involving Multiple Agents (1998)
While plan recognition research has been applied to a wide variety of problems, it has largely made identical assumptions about the number of agents participating in the plan, the observability of...
PML: Representing Procedural Domains for Multimedia Presentations (1998)
Ashwin Ram, Richard Catrambone, Mark J. Guzdial, Colleen M. Kehoe, D. Scott Mccrickard, John T. Stasko
A central issue in the development of multimedia systems is the presentation of the information to the user of the system and how to best represent that information to the designer of the system....
Opportunistic Enterprises in Invention (1998)
Marin Simina, Janet Kolodner, Ashwin Ram, Michael Gorman
This paper identifies goal handling processes that begin to account for the kind of processes involved in invention. We identify new goal properties and mechanisms for processing goals, as well as...
Experiments with Reinforcement Learning in Problems with Continuous State and Action Spaces (1998)
Juan Carlos Santamaría, Juan Carlos Santamar'ia, Richard S. Sutton, Ashwin Ram
A key element in the solution of reinforcement learning problems is the value function. The purpose of this function is to measure the long-term utility or value of any given state and it is...
Experiments with Reinforcement Learning in Problems with Continuous State and Action Spaces (1998)
Juan C. Santamaría, Juan C. Santamar'ia, A. Ram, R. Sutton, Ashwin Ram
A key element in the solution of reinforcement learning problems is the value function. The purpose of this function is to measure the long-term utility or value of any given state. The function is...
PML: Representing Procedural Domains for Multimedia Presentations (1998)
Ram, Ashwin, Catrambone, Richard, Guzdial, Mark, Kehoe, Colleen Mary, McCrickard, D. Scott, Stasko, John T.
A central issue in the development of multimedia systems is the presentation of the information to the user of the system and how to best represent that information to the designer of the system....
Semi-Annual Progress Report, 16 November 96 - 16 May 97 (Office of Naval Research). (1997)
Stasko, John, Catrambone, Richard, Guzdial, Mark, Ram, Ashwin
Our project focuses on researching and defining architecture guidelines for developing multimedia systems to support human learning. We base these guidelines on principles from cognitive science....
Multistrategy Learning of Adaptive Reactive Controllers (1997)
Santamaria, Juan Carlos, Ram, Ashwin
Reactive controllers has been widely used in mobile robots since they are able to achieve successful performance in real-time. However, the configuration of a reactive controller depends highly on...
A new heuristic approach for dual control (1997)
Juan C. Santamar'ia, Ashwin Ram
Autonomous agents engaged in a continuous interaction with an incompletely known environment face the problem of dual control [Fel'dbaum 1965]. Simply stated, actions are necessary not only for...
Learning of parameter-adaptive reactive controllers for robotic navigation (1997)
Juan C. Santamar'ia, Ashwin Ram
Reactive controllers are widely used in mobile robots because they are able to achieve successful performance in real-time. However, the configuration of a reactive controller depends highly on the...
Efficient Feature Selection in Conceptual Clustering (1997)
Feature selection has proven to be a valuable technique in supervised learning for improving predictive accuracy while reducing the number of attributes considered in a task. We investigate the...
Situation Development in a Complex Real-World Domain (1997)
Applying techniques from Machine Learning to real-world domains and problems often requires considerable processing of the input data, to both remove noise and to augment the amount and type of...
Case-Based Planning to Learn (1997)
J. William Murdock, Gordon Shippey, Ashwin Ram
. Learning can be viewed as a problem of planning a series of modifications to memory. We adopt this view of learning and propose the applicability of the case-based planning methodology to the task...
Efficient Feature Selection in Conceptual Clustering (1997)
Feature selection has proven to be a valuable technique in supervised learning for improving predictive accuracy while reducing the number of attributes considered in a task. We investigate the...
Multistrategy Learning of Adaptive Reactive Controllers (1997)
Juan Carlos Santamaria, Ashwin Ram
Reactive controllers has been widely used in mobile robots since they are able to achieve successful performance in real-time. However, the configuration of a reactive controller depends highly on...
A New Heuristic Approach for Dual Control (1997)
Juan C. Santamaría, Juan C. Santamar'ia, Ashwin Ram
Autonomous agents engaged in a continuous interaction with an incompletely known environment face the problem of dual control [Fel'dbaum 1965]. Simply stated, actions are necessary not only for...
A Computational Theory of Dynamical Modeling in Scientific Reasoning (1997)
Todd W. Griffith, Dr. N. Hari Narayanan, Dr. Ashwin Ram
The focus of this research is on dynamical modeling in scientific reasoning. Dynamical modeling uses, transforms, and constructs models which capture the causal and structural dynamics of given...
Multistrategy Learning of Adaptive Reactive Controllers (1997)
Santamaria, Juan Carlos, Ram, Ashwin
Reactive controllers has been widely used in mobile robots since they are able to achieve successful performance in real-time. However, the configuration of a reactive controller depends highly on...
A New Heuristic Approach for Dual Control (1997)
Ram, Ashwin, Santamaria, Juan Carlos
Autonomous agents engaged in a continuous interaction with an incompletely known environment face the problem of dual control [Fel’dbaum 1965]. Simply stated, actions are necessary not only for...
The Role of Student Tasks in Accessing Cognitive Media Types (1996)
Michael Byrne, Mark Guzdial, Preetha Ram, Richard Catrambone, Ashwin Ram, John Stasko, ...
: We believe that identifying media by their cognitive roles (e.g., definition, explanation, pseudo-code, visualization) can improve comprehension and usability in hypermedia systems designed for...
Systematic Evaluation of Design Decisions in Case-Based Reasoning Systems (1996)
Juan Carlos Santamaría, Juan Carlos Santamar'ia, Ashwin Ram
Introduction Two important goals in the evaluation of artificial intelligence (AI) systems are to assess the merit of alternative design decisions in the performance of an implemented computer system...
Exploring Interface Options in Multimedia Educational Environments (1996)
Gordon Shippey, Ashwin Ram, Florian Albrecht, Janis Roberts, Mark Guzdial, Richard Catrambone, ...
this paper. Finally, future systems can help us explore the learning itself, revealing students' strategies and understandings of their own learning processes. References
The Role of Ontology in Creative Understanding (1996)
Successful creative understanding requires that a reasoner be able to manipulateknown conceptsin order to understandnovel ones. A major problem arises, however, when one considers exactly how these...
Introspective multistrategy learning: On the construction of learning strategies (1996)
A central problem in multistrategy learning systems is the selection and sequencing of machine learning algorithms for particular situations. This is typically done by the system designer who...
Experiments With Reinforcement Learning in Problems With Continuous State and Action Spaces (1996)
Ram, Ashwin, Santamaria, Juan Carlos, Sutton, Richard S.
A key element in the solution of reinforcement learning problems is the value function. The purpose of this function is to measure the long-term utility or value of any given state and it is...
Structuring On-The-Job Troubleshooting Performance to Aid Learning (1995)
Brian Minsk, Harinarayanan Balakrishnan, Ashwin Ram
This paper describes a methodology for aiding the learning of troubleshooting tasks in the course of an engineer's work. The approach supports learning in the context of actual, on-the-job...
Learning as goal-driven inference (1995)
Ryszard S. Michalski, Ashwin Ram
A remarkable aspect of human learners is that they are able to apply a great variety of learning strategies in a flexible and goal-oriented manner and to dynamically accommodate the demands of...
Understanding the Creative Mind (1995)
Ashwin Ram, Linda Wills, Eric Domeshek, Nancy Nersessian, Janet Kolodner
We review Margaret Boden's book The Creative Mind, an excellent survey and synthesis of current computational theories of creativity. Boden's stated goal is to explain how creativity (as a...
Foundations Of Artificial, Ashwin Ram, Eric K. Jones
We review the book Foundations of Artificial Intelligence (ed. David Kirsch, MIT Press, Cambridge, MA, 1993) and present a framework for the analysis of theories of artificial intelligence....
A Comparative Utility Analysis of Case-Based Reasoning and Control-Rule Learning Systems (1995)
The utility problem in learning systems occurs when knowledge learned in an attempt to improve a system's performance degrades performance instead. We present a methodology for the analysis of...
Structuring On-The-Job Troubleshooting Performance To Aid Learning (1995)
Brian Minsk, Harinarayanan Balakrishnan, Ashwin Ram
This paper describes a methodology for aiding the learning of troubleshooting tasks in the course of an engineer's work. The approach supports learning in the context of actual, on-the-job...
Interacting Learning-Goals: Treating Learning as a Planning Task (1995)
. This research examines the metaphor of goal-driven planning as a tool for performing the integration of multiple learning algorithms. In case-based reasoning systems, several learning techniques...
Understanding the Creative Mind (1995)
Ashwin Ram, Linda Wills, Eric Domeshek, Nancy Nersessian, Janet Kolodner
This paper is based in part on research by Kenneth Moorman, who also provided us with helpful suggestions for improving this paper. We are grateful to our editors Mark Stefik and Stephen Smoliar for...
Contents Acknowledgements Preface by Professor Tom Mitchell, CMU Editors' Preface List of Contributors 1. Learning, Goals, and Learning Goals : : : : : : : : : : : : : : : : : : : : : : : : : :...
A Comparative Utility Analysis of Case-Based Reasoning and Control-Rule Learning Systems (1995)
The utility problem in learning systems occurs when knowledge learned in an attempt to improve a system 's performance degrades performance instead. We present a methodology for the analysis of...
Chapter 21 Learning as Goal-Driven Inference (1995)
ion Concretion Explanation Prediction Similization Dissimilization DEDUCTION INDUCTION Knowledge Generation Transmutations Transmutations Inference Type EQUIVALENCE NO INFERENCE Reformulation...
A Comparative Utility Analysis of Case-Based Reasoning and Control-Rule Learning Systems (1995)
The utility problem in learning systems occurs when knowledge learned in an attempt to improve a system's performance degrades performance instead. We present a methodology for the analysis of...
Syntax-Semantics Interaction In Sentence Understanding (1995)
Kavi Mahesh, Susan Bovair, Jennifer K. Holbrook, Ashwin Ram, J. Spencer Rugaber
Object) TEACH Event: officer child animate living human other-animal adult plant horse (a) Lexicalized Conceptual Knowledge (b) Non-Lexical Concept Hierarchies (or Graphs) physicalobject...
Cognitive Media Types for Multimedia Information Access (1995)
Mimi M. Recker, Ashwin Ram, Terry Shikano, George Li, John Stasko
Multimedia repositories, libraries, and databases offer the potential for providing students with access to a wide variety of interconnected information resources. However, in order to realize this...
Anthony G. Francis, Ashwin Ram
Solving problems in many real-world domains requires integrating knowledge from several past experiences. This integration requires the dynamic retrieval of multiple experiences and the extraction of...
A Functional Theory of Creative Reading (1994)
Reading is an area of human cognition which has been studied for decades by psychologists, education researchers, and artificial intelligence researchers. Yet, there still does not exist a theory...
A Functional Theory of Creative Reading (1994)
Kenneth Moorman Ashwin, Ashwin Ram
Reading is an area of human cognition which has been studied for decades by psychologists, education researchers, and artificial intelligence researchers. Yet, there still does not exist a theory...
Goal-Driven Learning: Fundamental Issues (A Symposium Report) (1994)
In Artificial Intelligence, Psychology, and Education, a growing body of research supports the view that learning is a goal-directed process. Psychological experiments show that people with different...
A Framework for Goal-Driven Learning (1994)
this paper, we describe a framework for goal-driven learning and its relationship to prior and current theories from each of these perspectives.
Dynamically Adjusting Concepts to Accommodate Changing Contexts (1994)
In concept learning, objects in a domain are grouped together based on similarity as determined by the attributes used to describe them. Existing concept learners require that this set of attributes...
AQUA: Questions that drive the explanation process (1994)
Ashwin Ram College, Ashwin Ram
explanation schemas for why people do things. These are standard highlevel explanations for actions, such as "Actor does action because the outcome of action satisfies a goal of the actor."...
A Framework for Goal-Driven Learning (1994)
this paper, we describe a framework for goal-driven learning and its relationship to prior and current theories from each of these perspectives.
A Model of Creative Understanding (1994)
Although creativity has largely been studied in problem solving contexts, creativity consists of both a generative component and a comprehension component. In particular, creativity is an essential...
Integrating Creativity and Reading: A Functional Approach (1994)
Reading has been studied for decades by a variety of cognitive disciplines, yet no theories exist which sufficiently describe and explain how people accomplish the complete task of reading real-world...
Cognitive Media Types as Indices for Hypermedia Learning Environments (1994)
In this paper, we propose a theoretical framework for designing indices for educational hypermedia systems. In this theory, we argue that the design of these systems and their and indices are best...
Ashwin Ram, Ronald Arkin, Gary Boone, Michael Pearce
This paper explores the application of genetic algorithms to the learning of local robot navigation behaviors for reactive control systems. Our approach evolves reactive control systems in various...
Systematic Evaluation of Design Decisions in CBR Systems (1994)
Juan Carlos Santamaría, Juan Carlos Santamar'ia, Ashwin Ram
Two important goals in the evaluation of an AI theory or model are to assess the merit of the design decisions in the performance of an implemented computer system and to analyze the impact in the...
Managing Learning Goals in Strategy-Selection Problems (1994)
In case-based reasoning systems, several learning techniques may apply to a given situation. In a failuredriven learning environment, the problems of strategy selection are to choose the best set of...
A Functional Theory of Creative Reading (1994)
Reading is an area of human cognition which has been studied for decades by psychologists, education researchers, and artificial intelligence researchers. Yet, there still does not exist a theory...
AQUA: Questions that drive the explanation process (1994)
explanation schemas for why people do things. These are standard high-level explanations for actions, such as "Actor does action because the outcome of action satisfies a goal of the...
Choosing Learning Strategies to Achieve Learning Goals (1994)
In open world applications a number of machine-learning techniques may potentially apply to a given learning situation. The research presented here illustrates the complexity involved in...
Introspective Reasoning Using Meta-Explanations for Multistrategy Learning (1994)
In order to learn effectively, a reasoner must not only possess knowledge about the world and be able to improve that knowledge, but it also must introspectively reason about how it performs a given...
Dynamically Adjusting Concepts to Accommodate Changing Contexts (1994)
In concept learning, objects in a domain are grouped together based on similarity as determined by the attributes used to describe them. Existing concept learners require that this set of attributes...
Managing learning goals in strategy-selection problems (1994)
In case-based reasoning systems, several learning techniques may apply to a given situation. In a failuredriven learning environment, the problems of strategy selection are to choose the best set of...
A functional theory of creative reading (1994)
Reading is an area of human cognition which has been studied for decades by psychologists, education researchers, and artificial intelligence researchers. Yet, there still does not exist a theory...
A Functional Theory of Creative Reading (1994)
Moorman, Kenneth Matthew, Ram, Ashwin
Reading is an area of human cognition which has been studied for decades by psychologists, education researchers, and artificial intelligence researchers. Yet, there still does not exist a theory...
Ram, Ashwin, Arkin, Ronald C., Boone, Gary Noel, Pearce, Michael
This paper explores the application of genetic algorithms to the learning of local robot navigation behaviors for reactive control systems. Our approach evolves reactive control systems in various...
AQUA: Questions that Drive the Explanation Process (1993)
In the doctoral dissertation from which this chapter is drawn, Ashwin Ram presented an alternative perspective on the processes of story understanding, explanation, and learning. The issues that Ram...
Ram, Ashwin, Narayanan, Sundaram, Cox, Michael Thomas
This article presents a computational model of the learning of diagnostic knowledge based on observations of human operators engaged in a real-world troubleshooting task. We present a model of...
Ashwin Ram, Juan Carlos Santamaría
This paper presents a self-improving reactive control system for autonomous robotic navigation. The navigation module uses a schemabased reactive control system to perform the navigation task. The...
This article presents a computational model of the learning of diagnostic knowledge based on observations of human operators engaged in a real-world troubleshooting task. We present a model of...
A New Perspective on Story Understanding (1993)
Reading has been studied for decades by both artificial intelligent researchers and by cognitive psychologists. Yet there still does not exist a theory which accurately describes the process nor a...
Ashwin Ram, Juan Carlos Santamaría
This paper presents a self-improving reactive control system for autonomous robotic navigation. The navigation module uses a schemabased reactive control system to perform the navigation task. The...
Creative Conceptual Change (1993)
Ashwin Ram, Kenneth Moorman, Juan Carlos Santamaría
Creative conceptual change involves (a) the construction of new concepts and of coherent belief systems, or theories, relating these concepts, and (b) the modification and extrapolation of existing...
Goal-Driven Learning: Fundamental Issues and Symposium Report (1993)
In Artificial Intelligence, Psychology, and Education, a growing body of research supports the view that learning is a goal-directed process. Psychological experiments show that people with different...
Indexing, Elaboration and Refinement: Incremental Learning of Explanatory Cases (1993)
This article describes how a reasoner can improve its understanding of an incompletely understood domain through the application of what it already knows to novel problems in that domain. Casebased...
Creative Conceptual Change (1993)
Ashwin Ram, Kenneth Moorman, Juan Carlos Santamara
Creative conceptual change involves (a) the construction of new concepts and of coherent belief systems, or theories, relating these concepts, and (b) the modification and extrapolation of existing...
Multistrategy Learning In Reactive Control Systems For Autonomous Robotic Navigation (1993)
Ashwin Ram, Juan Carlos Santamar'ia
This paper presents a self-improving reactive control system for autonomous robotic navigation. The navigation module uses a schema-based reactive control system to perform the navigation task. The...
The Utility Problem in Case Based Reasoning (1993)
Anthony G. Francis, Ashwin Ram
ed in Case-Based Reasoning: Papers from the 1993 Workshop, July 11-12, Washington, D.C., Technical Report WS-93-01, AAAI Press THE UTILITY PROBLEM IN CASE BASED REASONING ANTHONY G. FRANCIS ASHWIN...
Anthony Francis, Jr. Ashwin Ram
computational analysis of these factors. We use this method to analyze different types of problem solving systems, including unguided search, control rule, and case-based systems. While some aspects...
Knowledge Compilation and Speedup Learning in Continuous Task Domains (1993)
Juan Carlos Santamaria, Ashwin Ram
Many techniques for speedup learning and knowledge compilation focus on the learning and optimization of macro-operators or control rules in task domains that can be characterized using a...
Continuous Case-Based Reasoning (1993)
Ashwin Ram, Juan Carlos Santamaría
Case-based reasoning systems have traditionallybeen used to perform high-level reasoning in problem domains that can be adequately described using discrete, symbolic representations. However, many...
Creative Conceptual Change (1993)
Creative conceptual change involves (a) the construction of new concepts and of coherent belief systems, or theories, relating these concepts, and (b) the modification and extrapolation of existing...
Ashwin Ram, S. Narayanan, M. Cox
This article presents a computational model of the learning of diagnostic knowledge, based on observations of human operators engaged in a real-world troubleshooting task. We present a model of...
Indexing, Elaboration and Refinement: Incremental Learning of Explanatory Cases (1993)
This article describes how a reasoner can improve its understanding of an incompletely understood domain through the application of what it already knows to novel problems in that domain. Casebased...
Ashwin Ram, Juan Carlos Santamaría
This paper presents a self-improving reactive control system for autonomous robotic navigation. The navigation module uses a schemabased reactive control system to perform the navigation task. The...
AQUA: Questions that Drive the Explanation Process (1993)
In the doctoral dissertation from which this chapter is drawn, Ashwin Ram presented an alternative perspective on the processes of story understanding, explanation, and learning. The issues that Ram...
Ram, Ashwin, Narayanan, Sundaram, Cox, Michael Thomas
This article presents a computational model of the learning of diagnostic knowledge based on observations of human operators engaged in a real-world troubleshooting task. We present a model of...
Knowledge Compilation and Speedup Learning in Continuous Task Domains (1993)
Ram, Ashwin, Santamaria, Juan Carlos
Many techniques for speedup learning and knowledge compilation focus on the learning and optimization of macro-operators or control rules in task domains that can be characterized using a...
Ram, Ashwin, Santamaria, Juan Carlos
This paper presents a self-improving reactive control system for autonomous robotic navigation. The navigation module uses a schema-based reactive control system to perform the navigation task. The...
Multistrategy Learning in Reactive Control Systems for Autonomous Robotic Navigation (1993)
Ram, Ashwin, Santamaria, Juan Carlos
This paper presents a self-improving reactive control system for autonomous robotic navigation. The navigation module uses a schema-based reactive control system to perform the navigation task. The...
Learning Momentum: On-line Performance Enhancement for Reactive Systems (1992)
Russell Clark, Ronald C. Arkin, Ashwin Ram
We describe a reactive robotic control system which incorporates aspects of machine learning to improve the system's ability to successfully navigate in unfamiliar environments. This system...
The Use of Explicit Goals for Knowledge to Guide Inference and Learning (1992)
Ashwin Ram College, Ashwin Ram, Lawrence Hunter
Combinatorial explosion of inferences has always been a central problem in artificial intelligence. Although the inferences that can be drawn from a reasoner's knowledge and from available...
A Case-Based Approach to Reactive Control for Autonomous Robots (1992)
We propose a case-based method of selecting behavior sets as an addition to traditional reactive robotic control systems. The new system (ACBARR --- A Case BAsed Reactive Robotic system) provides...
An Architecture for Integrated Introspective Learning (1992)
Ashwin Ram, Michael T. Cox, S. Narayanan
This paper presents a computational model of integrated introspective learning, which is a deliberative learning process in which a reasoner introspects about its own performance on a reasoning task,...
An Explicit Representation Of Forgetting (1992)
A pervasive, yet much ignored, factor in the analysis of processing-failures is the problem of misorganized knowledge. If a system's knowledge is not indexed or organized correctly, it may make...
The Use of Explicit Goals for Knowledge to Guide Inference and Learning (1992)
Combinatorial explosion of inferences has always been a central problem in artificial intelligence. Although the inferences that can be drawn from a reasoner's knowledge and from available...
The Learning of Reactive Control Parameters Through Genetic Algorithms (1992)
Michael Pearce, Ronald Arkin, Ashwin Ram
This paper explores the application of genetic algorithms to the learning of local robot navigation behaviors for reactive control systems. Our approach is to train a reactive control system in...
Learning Momentum: On-line Performance Enhancement for Reactive Systems (1992)
Russell J. Clark, Ronald C. Arkin, Ashwin Ram
We describe a reactive robotic control system which incorporates aspects of machine learning to improve the system's ability to successfully navigate in unfamiliar environments. This system...
Ram, Ashwin, Arkin, Ronald C., Clark, Russell J., Moorman, Kenneth
This article presents a new line of research investigating on-line learning mechanisms for autonomous intelligent agents. We discuss a case-based method for dynamic selection and modification of...
Learning Momentum: On-Line Performance Enhancement for Reactive Systems (1992)
Arkin, Ronald C., Clark, Russell J., Ram, Ashwin
We describe a reactive robotic control system which incorporates aspects of machine learning to improve the system's ability to successfully navigate in unfamiliar environments. This system overcomes...
The Learning of Reactive Control Parameters Through Genetic Algorithms (1992)
Arkin, Ronald C., Pearce, Michael, Ram, Ashwin
This paper explores the application of genetic algorithms to the learning of local robot navigation behaviors for reactive control systems. Our approach is to train a reactive control system in...
A Case-Based Approach to Reactive Control for Autonomous Robots (1992)
We propose a case-based method of selecting behavior sets as an addition to traditional reactive robotic control systems. The new system (ACBARR - A Case BAsed Reactive Robotic system) provides more...
A Theory of Questions and Question Asking (1991)
Ashwin Ram College, Ashwin Ram
This article focusses on knowledge goals, that is, the goals of a reasoner to acquire or reorganize knowledge. Knowledge goals, often expressed as questions, arise when the reasoner's model of...
Using Introspective Reasoning to Select Learning Strategies (1991)
In order to learn effectively, a system must not only possess knowledge about the world and be able to improve that knowledge, but it also must introspectively reason about how it performs a given...
A Goal-Based Approach to Intelligent Information Retrieval (1991)
Intelligent information retrieval (IIR) requires inference. The number of inferences that can be drawn by even a simple reasoner is very large, and the inferential resources available to any...
A Theory of Questions and Question Asking (1991)
This article focusses on knowledge goals, that is, the goals of a reasoner to acquire or reorganize knowledge. Knowledge goals, often expressed as questions, arise when the reasoner's model of...
Learning Indices for Schema Selection (1991)
In addition to learning new knowledge, a system must be able to learn when the knowledge is likely to be applicable. An index is a piece of information which, when identified in a given situation,...
Interest-Based Information Filtering and Extraction in Natural Language Understanding Systems (1991)
Given the vast amount of information available to the average person, there is a growing need for mechanisms that can select relevant or useful information based on some specification of the...
Evaluation of Explanatory Hypotheses (1991)
Abduction is often viewed as inference to the "best" explanation. However, the evaluation of the goodness of candidate hypotheses remains an open problem. Most artificial intelligence...
Goal-Driven Learning in Multistrategy Reasoning and Learning Systems (1991)
Introduction This chapter presents a computational model of introspective multistrategy learning, which is a deliberative or strategic learning process in which a reasoner introspects about its own...
Interest-based Information Filtering and Extraction in Natural Language Understanding Systems (1991)
Given the vast amount of information available to the average person, there is a growing need for mechanisms that can select relevant or useful information based on some specification of the...
Incremental Learning of Explanation Patterns and their Indices (1990)
This paper describes how a reasoner can improve its understanding of an incompletely understood domain through the application of what it already knows to novel problems in that domain. Recent work...
Knowledge Goals: A Theory of Interestingness (1990)
Combinatorial explosion of inferences has always been one of the classic problems in AI. Resources are limited, and inferences potentially infinite; a reasoner needs to be able to determine which...
Decision Models: A Theory of Volitional Explanation (1990)
This paper presents a theory of motivational analysis, the construction of volitional explanations to describe the planning behavior of agents. We discuss both the content of such explanations, as...
Ashwin Ram, Ronald C. Arkin, Kenneth Moorman, Russell J. Clark
This article presents a new line of research investigating on-line learning mechanisms for autonomous intelligent agents. We discuss a case-based method for dynamic selection and modification of...