A set of hypotheses is formulated for a connectionist approach to cognitive modeling. These hypotheses are shown to be incompatible with the hypotheses underlying traditional cognitive models. The connectionist models considered are massively parallel numerical computational systems that are a kind of continuous dynamical system. The numerical variables in the system correspond semantically to fine-grained features below the level of the concepts consciously used to describe the task domain. The level of analysis is intermediate between those of symbolic cognitive models (...) and neural models. The explanations of behavior provided are like those traditional in the physical sciences, unlike the explanations provided by symbolic models. (shrink)

As new unanticipated items are added to a memory, it must be able to reorganize itself, integrating the new items into its structure. The reorganization process must maintain the memory's structure and also build up the knowledge retrieval strategies need to search that structure. This study will present an algorithm for knowledge‐based memory reorganization. Included in that algorithm are processes for directed generalization and generalization refinement. A fact retrieval system called CYRUS which uses the algorithm is also presented. Conclusions are (...) drawn about maintaining accessibility in a conceptual memory, organizing generalized knowledge with respect to specific knowledge, and expected retrieval failures due to change over time in the memory's organization. (shrink)

At present, the prevailing Connectionist methodology forrepresenting rules is toimplicitly embody rules in neurally-wired networks. That is, the methodology adopts the stance that rules must either be hard-wired or trained into neural structures, rather than represented via explicit symbolic structures. Even recent attempts to implementproduction systems within connectionist networks have assumed that condition-action rules (or rule schema) are to be embodied in thestructure of individual networks. Such networks must be grown or trained over a significant span of time. However, arguments (...) are presented herein that humanssometimes follow rules which arevery rapidly assignedexplicit internal representations, and that humans possessgeneral mechanisms capable of interpreting and following such rules. In particular, arguments are presented that thespeed with which humans are able to follow rules ofnovel structure demonstrates the existence of general-purpose rule following mechanisms. It is further argued that the existence of general-purpose rule following mechanisms strongly indicates that explicit rule following is not anisolated phenomenon, but may well be a common and important aspect of cognition. The relationship of the foregoing conclusions to Smolensky''s view of explicit rule following is also explored. The arguments presented here are pragmatic in nature, and are contrasted with thekind of arguments developed by Fodor and Pylyshyn in their recent, influential paper. (shrink)

Time underlies many interesting human behaviors. Thus, the question of how to represent time in connectionist models is very important. One approach is to represent time implicitly by its effects on processing rather than explicitly (as in a spatial representation). The current report develops a proposal along these lines first described by Jordan (1986) which involves the use of recurrent links in order to provide networks with a dynamic memory. In this approach, hidden unit patterns are fed back to themselves: (...) the internal representations which develop thus reflect task demands in the context of prior internal states. A set of simulations is reported which range from relatively simple problems (temporal version of XOR) to discovering syntactic/semantic features for words. The networks are able to learn interesting internal representations which incorporate task demands with memory demands: indeed, in this approach the notion of memory is inextricably bound up with task processing. These representations reveal a rich structure, which allows them to be highly context‐dependent, while also expressing generalizations across classes of items. These representations suggest a method for representing lexical categories and the type/token distinction. (shrink)

This systematic investigation of computation and mental phenomena by a noted psychologist and computer scientist argues that cognition is a form of computation, that the semantic contents of mental states are encoded in the same general way as computer representations are encoded. It is a rich and sustained investigation of the assumptions underlying the directions cognitive science research is taking. 1 The Explanatory Vocabulary of Cognition 2 The Explanatory Role of Representations 3 The Relevance of Computation 4 The Psychological Reality (...) of Programs: Strong Equivalence 5 Constraining Functional Architecture 6 The Bridge from Physical to Symbolic: Transduction 7 Functional Architecture and Analogue Processes 8 Mental Imagery and Functional Architecture 9 Epilogue: What is Cognitive Science the Science of? (shrink)

Computation is a process of making explicit, information that was implicit. In computing 5 as the solution to ∛125, for example, we move from a description that is not explicitly about 5 to one that is. We are drawing out numerical consequences to the description ∛125. We are extracting information implicit in the problem statement. Can we precisely state the difference between information thati s implicit in a state, structure or process and information that is explicit?