Archive for the ‘Learning’ Category

Invention as an Opportunistic Enterprise

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 processing such goals, as well as means of integrating opportunism, deliberation, and social interaction into goal/plan processes. We focus on invention goals, which address significant enterprises associated with an inventor. Invention goals represent “seed” goals of an expert, around which the whole knowledge of an expert gets reorganized and grows more or less opportunistically. Invention goals reflect the idiosyncrasy of thematic goals among experts. They constantly increase the sensitivity of individuals for particular events that might contribute to their satisfaction.

Our exploration is based on a well-documented example: the invention of the telephone by Alexander Graham Bell. We propose mechanisms to explain: (1) how Bell’s early thematic goals gave rise to the new goals to invent the multiple telegraph and the telephone, and (2) how the new goals interacted opportunistically. Finally, we describe our computational model, ALEC, that accounts for the role of goals in invention.

Invention as an Opportunistic Enterprise

by Marin Simina, Janet Kolodner, Ashwin Ram, Michael Gorman

19th Annual Conference of the Cognitive Science Society, Stanford, CA, August 1997
www.cc.gatech.edu/faculty/ashwin/papers/git-cs-97-04.pdf

A New Heuristic Approach for Dual Control

Autonomous agents engaged in a continuous interaction with an incompletely known environment face the problem of dual control (Feldbaum, 1965). Simply stated, actions are necessary not only for studying the environment, but also for making progress on the task. In other words, actions must bear a “dual” character: They must be investigators to some degree, but also directors to some degree. Because the number of variables involved in the solution of the dual control problem increases with the number of decision stages, the exact solution of the dual control problem is computationally intractable except for a few special cases.

This paper provides an overview of dual control theory and proposes a heuristic approach towards obtaining a near-optimal dual control method that can be implemented. The proposed algorithm selects control actions taking into account the information contained in past observations as well as the possible information that future observations may reveal. In short, the algorithm anticipates the fact that future learning is possible and selects the control actions accordingly. The algorithm uses memory-based methods to associate long-term benefit estimates to belief states and actions, and selects the actions to execute next according to such estimates. The algorithm uses the outcome of every experience to progressively refine the long-term benefit estimates so that it can make better, improved decisions as it progresses. The algorithm is tested on a classical simulation problem.

Read the paper:

A New Heuristic Approach for Dual Control

by Juan Carlos Santamaria, Ashwin Ram

AAAI-97 Workshop on On-Line Search, Providence, RI, July 1997
www.cc.gatech.edu/faculty/ashwin/papers/er-97-02.pdf

Can Your Architecture Do This? A Proposal for Impasse-Driven Asynchronous Memory Retrieval and Integration

We propose an impasse-driven method for generating memory retrieval requests and integrating their contents dynamically and asynchronously into the current reasoning context of an agent. This method extends our previous theory of agent architecture, called experience-based agency (Ram & Francis 1996), by proposing a general method that can replace and augment task-specific mechanisms for generating memory retrievals and invoking integration mechanisms. As part of an overall agent architecture, this method has promise as a way to introduce in a principled way efficient high-level memory operations into systems based on reactive task-network decomposition.

Read the paper:

Can Your Architecture Do This? A Proposal for Impasse-Driven Asynchronous Memory Retrieval and Integration

by Anthony Francis, Ashwin Ram

AAAI-97 Workshop on Robots, Softbots, Immobots: Theories of Action, Planning and Control, Providence, RI, July 1997
www.cc.gatech.edu/faculty/ashwin/papers/er-97-03.pdf

Case-Based Planning to Learn

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 of planning to learn. We argue that relatively simple, fine-grained primitive inferential operators are needed to support flexible planning. We show that it is possible to obtain the benefits of case-based reasoning within a planning to learn framework.

Read the paper:

Case-Based Planning to Learn

by Bill Murdock, Gordon Shippey, Ashwin Ram

2nd International Conference on Case-Based Reasoning (ICCBR-97), Providence, RI, July 1997
www.cc.gatech.edu/faculty/ashwin/papers/er-97-04.pdf

Efficient Feature Selection in Conceptual Clustering

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 potential for similar benefits in an unsupervised learning task, conceptual clustering. The issues raised in feature selection by the absence of class labels are discussed and an implementation of a sequential feature selection algorithm based on an existing conceptual clustering system is described. Additionally, we present a second implementation which employs a technique for improving the efficiency of the search for an optimal description and compare the performance of both algorithms.

Read the paper:

Efficient Feature Selection in Conceptual Clustering

by Mark Devaney, Ashwin Ram

14th  International Conference on Machine Learning (ICML-97), Nashville, TN, July 1997
www.cc.gatech.edu/faculty/ashwin/papers/er-97-01.pdf

Situation Development in a Complex Real-World Domain

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 information present. We describe our work in the task of situation assessment in the domain of US Army training exercises involving hundreds of agents interacting in real-time over the course of several days. In particular, we describe techniques we have developed to process this data and draw general conclusions on the types of information required in order to apply various Machine Learning algorithms and how this information may be extracted in real-world situations where it is not directly represented.

Read the paper:

Situation Development in a Complex Real-World Domain

by Mark Devaney and Ashwin Ram

International Conference on Machine Learning (ICML-97) Workshop on Machine Learning Applications in the Real World, Nashville, TN, July 1997
www.cc.gatech.edu/faculty/ashwin/papers/er-97-05.pdf

A Functional Theory of Creative Reading: Process, Knowledge, and Evaluation

Reading is a complex cognitive behavior, making use of dozens of tasks to achieve comprehension. As such, it represents an important aspect of general cognition; the benefits of having a theory of reading would be far-reaching. Additionally, there is an aspect of reading which has been largely ignored by the research, namely, reading appears to encompass a creative process. In this dissertation, I present a theory capable of explaining creative reading. There are not separate reading behaviors, some mundane and some creative; instead, all of reading must be understood as a creative process. Therefore, a comprehensive theory of reading and creativity is needed. Unfortunately, although the scientific study of reading has been undertaken for almost a century, it is often done in a piecemeal fashion–that is, the research has often concentrated on a narrow aspect of reading behavior. This is due, to some degree, to the fact that reading is a huge process–however, it is my belief that failing to consider the complete reading process will limit the research, Thus, in my work, I identify a set of tasks which sufficiently covers the reading process for short narratives. Together, these tasks form the basis of a functional theory of reading.

Using the reading framework to support the research, I produced a theory of creative understanding, which is the process by which novel concepts come to be understood by a reasoner. To accomplish this, I created a taxonomy of novelty types, I produced a knowledge representation and ontology of sufficient flexibility to permit the representation of a wide-range of conceptual forms, and I created an interlocking set of four tasks which act together to produce the behavior–memory retrieval, analogical mapping, base-constructive analogy, and problem reformulation. My technique for base-constructive analogy is one of the more unique features of my work; it permits existing concepts to be combined in ways which enable novel concepts to be understood. In addition to that, the theory provides for reasonable bounding to occur on the process of creative understanding through a set of heuristics associated with the ontology. This allows reasonable bounding to occur while greatly reducing the possibility of non-useful understandings.

The theory of creative reading is instantiated in a computer model, the ISAAC system, which reads and comprehends short science fiction stories. The model has allowed me to perform empirical evaluation, providing an important stage in the overall theory revision cycle. The evaluation demonstrated that ISAAC can answer independently-generated comprehension questions about a set of science fiction stories with skill comparable to a group of college students. This result, along with an analysis of the internal workings of the model enables me to claim that my theory of creative reading is sufficient to explain important aspects of the behavior.

Read the thesis:

A functional theory of creative reading: Process, knowledge, and evaluation

by Kenneth Moorman

PhD Thesis, College of Computing, Georgia Institute of Technology, Atlanta, GA, 1997
www.cs.transy.edu/kmoorman/Dissertation/

Continuous Case-Based Reasoning

Case-based reasoning systems have traditionally been used to perform high-level reasoning in problem domains that can be adequately described using discrete, symbolic representations. However, many real-world problem domains, such as autonomous robotic navigation, are better characterized using continuous representations. Such problem domains also require continuous performance, such as on-line sensorimotor interaction with the environment, and continuous adaptation and learning during the performance task.

This article introduces a new method for continuous case-based reasoning, and discusses its application to the dynamic selection, modification, and acquisition of robot behaviors in an autonomous navigation system, SINS (Self-Improving Navigation System). The computer program and the underlying method are systematically evaluated through statistical analysis of results from several empirical studies. The article concludes with a general discussion of case-based reasoning issues addressed by this research.

Read the paper:

Continuous Case-Based Reasoning

by Ashwin Ram, Juan Carlos Santamaria

Artificial Intelligence journal, (90)1-2:25-77, 1997
www.cc.gatech.edu/faculty/ashwin/papers/er-97-06.pdf

Learning Adaptive Reactive Controllers

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 the operating conditions of the robot and the environment; thus, a reactive controller configured for one class of environments may not perform adequately in another. This paper presents a formulation of learning adaptive reactive controllers. Adaptive reactive controllers inherit all the advantages of traditional reactive controllers, but in addition they are able to adjust themselves to the current operating conditions of the robot and the environment in order to improve task performance. Furthermore, learning adaptive reactive controllers can learn when and how to adapt the reactive controller so as to achieve effective performance under different conditions.

The paper presents an algorithm for a learning adaptive reactive controller that combines ideas from case-based reasoning and reinforcement learning to construct a mapping between the operating conditions of a controller and the appropriate controller configuration; this mapping is in turn used to adapt the controller configuration dynamically. As a case study, the algorithm is implemented in a robotic navigation system that controls a Denning MRV-III mobile robot. The system is extensively evaluated using statistical methods to verify its learning performance and to understand the relevance of different design parameters on the performance of the system.

Read the paper:

Learning Adaptive Reactive Controllers

by Juan Carlos Santamaria, Ashwin Ram

Technical Report GIT-CC-97/05, College of Computing, Georgia Institute of Technology, Atlanta, GA, January 1997
www.cc.gatech.edu/faculty/ashwin/papers/git-cc-97-05.pdf

Systematic Evaluation of Design Decisions in Case-Based Reasoning Systems

Two important goals in the evaluation of artificial intelligence systems are to assess the merit of alternative design decisions in the performance of an implemented computer system and to analyze the impact in the performance when the system faces problem domains with different characteristics. Achieving these objectives enables us to understand the behavior of the system in terms of the theory and design of the computational model, to select the best system configuration for a given domain, and to predict how the system will behave when the characteristics of the domain or problem change. In addition, for case-based reasoning and other machine learning systems, it is important to evaluate the improvement in the performance of the system with experience (or with learning), to show that this improvement is statistically significant, to show that the variability in performance decreases with experience (convergence), and to analyze the impact of the design decisions on this improvement in performance.

We present a methodology for the evaluation of CBR and other AI systems through systematic empirical experimentation over a range of system configurations and environmental conditions, coupled with rigorous statistical analysis of the results of the experiments. We illustrate this methodology with a case study in which we evaluate a multistrategy case-based and reinforcement learning system which performs autonomous robotic navigation. In this case study, we evaluate a range of design decisions that are important in CBR systems, including configuration parameters of the system (e.g., overall size of the case library, size or extent of the individual cases), problem characteristics (e.g., problem difficulty), knowledge representation decisions (e.g., choice of representational primitives or vocabulary), algorithmic decisions (e.g., choice of adaptation method), and amount of prior experience (e.g., learning or training). We show how our methodology can be used to evaluate the impact of these decisions on the performance of the system and, in turn, to make the appropriate choices for a given problem domain and verify that the system does behave as predicted.

Read the paper:

Systematic Evaluation of Design Decisions in Case-Based Reasoning Systems

by Juan Carlos Santamaria, Ashwin Ram

In Case-Based Reasoning: Experiences, Lessons, and Future Directions, D.B. Leake, editor, AAAI Press, 1996
www.cc.gatech.edu/faculty/ashwin/papers/er-96-05.pdf