A computer program capable of acting intelligently in the world must have a general representation of the world in terms of which its inputs are interpreted. Designing such a program requires commitments about what knowledge

Abstract not found

Does knowledge of language consist of mentally-represented rules? Rumelhart and McClelland have described a connectionist (parallel distributed processing) model of the acquisition of the past tense in English which successfully maps many stems onto their past tense forms, both regular (walk/walked) and irregular (go/went), and which mimics some of the errors and sequences of development of children. Yet the model contains no explicit rules, only a set of neuron-style units which stand for trigrams of phonetic features of the stem, a set of units which stand for trigrams of phonetic features of the past form, and an array of connections between the two sets of units whose strengths are modified during learning. Rumelhart and McClelland conclude that linguistic rules may be merely convenient approximate fictions and that the real causal processes in language use and acquisition must be characterized as the transfer of activation levels among units and the modification of the weights of their connections. We analyze both the linguistic and the developmental assumptions of the model in detail and discover that (1) it cannot represent certain words, (2) it cannot learn many rules, (3) it can learn rules found in no human language, (4) it cannot explain morphological and phonological regularities, (5) it cannot explain the differences between irregular and regular forms, (6) it fails at its assigned task of mastering the past tense of English, (7) it gives an incorrect explanation for two developmental phenomena: stages of overregularization of irregular forms such as bringed, and the appearance of doubly-marked forms such as ated, and (8) it gives accounts of two others (infrequent overregularization of verbs ending in t/d, and the order of acquisition of different irregula...

In this report we show how the class of adaptive prediction methods that Sutton called "temporal difference," or TD, methods are related to the theory of squential decision making. TD methods have been used as "adaptive critics" in connectionist learning systems, and have been proposed as models of animal learning in classical conditioning experiments. Here we relate TD methods to decision tasks formulated in terms of a stochastic dynamical system whose behavior unfolds over time under the influence of a decision maker's actions. Strategies are sought for selecting actions so as to maximize a measure of long-term payoff gain. Mathematically, tasks such as this can be formulated as Markovian decision problems, and numerous methods have been proposed for learning how to solve such problems. We show how a TD method can be understood as a novel synthesis of concepts from the theory of stochastic dynamic programming, which comprises the standard method for solving such tasks when a model of the dynamical system is available, and the theory of parameter estimation, which provides the appropriate context for studying learning rules in the form of equations for updating associative strengths in behavioral models, or connection weights in connectionist networks. Because this report is oriented primarily toward the non-engineer interested in animal learning, it presents tutorials on stochastic sequential decision tasks, stochastic dynamic programming, and parameter estimation.

Behavior-oriented AI is a scientific discipline that studies how behavior of agents emerges and becomes intelligent and adaptive. Success of the field is defined in terms of success in building physical agents that are capable of maximising their own self-preservation in interaction with a dynamically changing environment. The paper addresses this artificial life route towards artificial intelligence and reviews some of the results obtained so far. 1 Official reference: Steels, L. (1994) The artificial life roots of artificial intelligence. Artificial Life Journal, Vol 1,1. MIT Press, Cambridge. 1 Introduction For several decades, the field of Artificial Intelligence has been pursuing the study of intelligent behavior using the methodology of the artificial [104]. But the focus of this field, and hence the successes, have mostly been on higher order cognitive activities such as expert problem solving. The inspiration for AI theories has mostly come from logic and the cognitive...

Search for conjunctions of highly discriminable features can be rapid or even parallel. This article explores, three possible accounts based on (a) perceptual segregation, (b) conjunction detectors, and (c) inhibition controlled separately by two or more distractor features. Search rates for conjunctions of color, size, orientation, and direction of motion correlated closely with an independent measure of perceptual segregation. However, they appeared unrelated to the physi-ology of single-unit responses. Each dimension contributed additively to conjunction search rates, suggesting that each was checked independently of the others. Unknown targets appear to be found only by serial search for each in turn. Searching through 4 sets of distractors was slower than searching through 2. The results suggest a modification of feature integration theory, in which attention is controlled not only by a unitary "window " but also by a form of feature-based inhibition. Objects in the real world vary in a large number of prop-erties, at least some of which appear to be coded by special-ized, independent channels or modules in the perceptual

An approach to connectionist natural language processing is proposed, which is based on hierarchically organized modular Parallel Distributed Processing (PDP) networks and a central lexicon of distributed input/output representations. The modules communicate using these representations, which are global and publicly available in the system. The representations are developed automatically by all networks while they are learning their processing tasks. The resulting representations reflect the regularities in the subtasks, which facilitates robust processing in the face of noise and damage, supports improved generalization, and provides expectations about possible contexts. The lexicon can be extended by cloning new instances of the items, that is, by generating a number of items with known processing properties and distinct identities. This technique combinatorially increases the processing power of the system. The recurrent FGREP module, together with a central lexicon, is used as a ba...

It has long been recognized that hierarchical problem solving can be used to reduce search. Yet, there has been little analysis of the problemsolving method and few experimental results. This paper provides the first comprehensive analytical and empirical demonstrations of the effectiveness of hierarchical problem solving. First, the paper shows analytically that hierarchical problem solving can reduce the size of the searchspace from exponential to linear in the solution length and identifies a sufficient set of assumptions for such reductions in search. Second, it presents empirical results both in a domain that meets all of these assumptions as well as in domains in which these assumptions do not strictly hold. Third, the paper explores the conditions under which hierarchical problem solving will be effective in practice.

Abstract not found

Analysis and experiments have shown that hierarchical problem-solving is most effective when the hierarchy satisfies the downward refinement property (DRP), whereby every abstract solution can be refined to a concrete-level solution without backtracking across abstraction levels. However, the DRP is a strong requirement that is not often met in practice. In this paper we examine the case when the DRP fails, and provide an analytical model of search complexity parameterized by the probability of an abstract solution being refinable. Our model provides a more accurate picture of the effectiveness of hierarchical problem-solving. We then formalize the DRP in Abstrips-style hierarchies, providing a syntactic test that can be applied to determine if a hierarchy satisfies the DRP. Finally, we describe an algorithm called Highpoint that we have developed. This algorithm builds on the Alpine algorithm of Knoblock in that it automatically generates abstraction hierarchies. However, it uses th...