Open AccessProceedings Article
Learning about systems that contain state variables
Thomas G. Dietterich
- pp 96-100
TLDR
This paper formalizes this learning problem and presents a method called the iterative extension method for solving it, which is being implemented and applied to the problem of learning UNIX file system commands by observing a tutorial interaction with UNIX.Abstract:
It is difficult to learn about systems that contain state variables when those variables are not directly observable. This paper formalizes this learning problem and presents a method called the iterative extension method for solving it. In the iterative extension method, the learner gradually constructs a partial theory of the state-containing system. At each stage, the learner applies this partial theory to interpret the I/O behavior of the system and obtain additional constraints on the structure and values of its state variables. These constraints can be applied to extend the partial theory by hypothesizing additional internal state variables. The improved theory can then be applied to interpret more complex I/O behavior. This process continues until a theory of the entire system is obtained. Several sufficient conditions for the success of this method are presented including (a) the observability and decomposability of the state information in the system, (b) the learnability of individual state transitions in the system, (c) the ability of the learner to perform synthesis of straight-line programs and conjunctive predicates from examples and (d) the ability of the learner to perform theory-driven data interpretation. The method is being implemented and applied to the problem of learning UNIX file system commands by observing a tutorial interaction with UNIX.read more
Citations
More filters
RESIDUE: a deductive approach to design synthesis
TL;DR: It is shown how Residue can avoid backtracking caused by making design decisions of overly coarse granularity, and is given a rule for constraint propagation in deductive synthesis, and its use in pruning the design space.
Proceedings Article
Learning procedures from examples and by doing
TL;DR: A program that learns procedures by examining worked-out examples in a textbook and by learning by working problems two kinds of production rules are created: working forward rules that produce an action when a proceduie is executed and difference rules that suggest operators from observed transformations.
Journal ArticleDOI
Learning about hidden events in system interactions
Stephen M. Casner,Clayton Lewis +1 more
TL;DR: ExPL model of causal analysis is extended, incorporating ideas from Miyake, Draper, and Dietterich, to give an account of learning about hidden events from examples, suggesting that violations of user expectations trigger a process in which hidden events are hypothesized and subsequently linked to user actions.
Proceedings ArticleDOI
Abstraction mechanisms in discrete-event inductive modeling
TL;DR: By making useful abstractions, the fundamental problem of insufficient knowledge in the realm of inductive modeling is tackled, which can predict a system's unobserved behavior according to a well-defined framework of discrete-event inductive modeled.
Book ChapterDOI
Knowledge Compilation to Speed Up Numerical Optimisation
TL;DR: A method to replace a single inefficient non-gradient-based optimization by a set of efficient numerical gradient-directed optimizations that can be performed in parallel and decreases the dependence of the numerical methods on having a good starting point is described.
References
More filters
Journal ArticleDOI
A theory and methodology of inductive learning
TL;DR: The authors view inductive learning as a heuristic search through a space of symbolic descriptions, generated by an application of various inference rules to the initial observational statements, including generalization rules, which perform generalizing transformations on descriptions, and conventional truth-preserving deductive rules.
Book ChapterDOI
Learning Efficient Classification Procedures and Their Application to Chess End Games
TL;DR: A series of experiments dealing with the discovery of efficient classification procedures from large numbers of examples is described, with a case study from the chess end game king-rook versus king-knight.
Book
A Structure for Plans and Behavior
TL;DR: Progress to date in the ability of a computer system to understand and reason about actions is described, and the structure of a plan of actions is as important for problem solving and execution monitoring as the nature of the actions themselves.
Dissertation
Learning Structural Descriptions From Examples
TL;DR: In this paper, the authors propose a method to solve the problem of energy efficiency in the context of electrical engineering, and demonstrate that it can be achieved by using energy minimization techniques.
Journal ArticleDOI
Forward reasoning and dependency-directed backtracking in a system for computer-aided circuit analysis
TL;DR: In this paper, a rule-based system for computer-aided circuit analysis, called EL, is presented, which is written in a rule language called ARS, and implemented by ARS as pattern-directed invocation demons monitoring an associative data base.