This paper presents a skill learning model CLARION. Different from existing models of mostly high-level skill learning that use a top-down approach (that is, turning declarative knowledge into procedural knowledge through practice), we adopt a bottom-up approach toward low-level skill learning, where procedural knowledge develops first and declarative knowledge develops later. Our model is formed by integrating connectionist, reinforcement, and symbolic learning methods to perform on-line reactive learning. It adopts a two-level dual-representation framework (Sun, 1995), with a combination of localist and distributed representation. We compare the model with human data in a minefield navigation task, demonstrating some match between the model and human data in several respects.

3 experiments were designed to demonstrate that classifying new letter strings as grammatical (i.e., conforming to a set of rules called a synthetic grammar) or ungrammatical may proceed from fragmentary conscious knowledge of the bigrams constituting the grammatical strings displayed in the study phase, rather than from an unconscious structured representation of the grammar, as Reber (1989) contended. In Experiment 1, grammaticality judgments of subjects initially studying grammatical letter strings did not differ from judgments by subjects learning from a list of the bigrams making up these strings. In Experiment 2, judgments about nongram-matical strings composed of valid bigrams placed in invalid locations were extremely poor, although better than chance. In Experiment 3 the explicit knowledge of bigrams as assessed by a recognition procedure appeared sufficient to account for observed performance on a standard test of grammaticality. A widely held model of cognition endows human subjects with the ability to implicitly abstract the regularities or high-level rules embodied in richly structured stimulus domains. Over the last 20 years, this general model has received strong

: This paper presents a novel learning model Clarion, which is a hybrid model based on the twolevel approach proposed in Sun (1995). The model integrates neural, reinforcement, and symbolic learning methods to perform on-line, bottom-up learning (i.e., learning that goes from neural to symbolic representations). The model utilizes both procedural and declarative knowledge (in neural and symbolic representations respectively), tapping into the synergy of the two types of processes. It was applied to deal with sequential decision tasks. Experiments and analyses in various ways are reported that shed light on the advantages of the model. obstacles agent target Figure 1: Navigating Through A Minefield 1 Introduction This paper presents a model that unifies neural, symbolic, and reinforcement learning. It addresses the following three issues: (1) It deals with autonomous learning: It allows a situated agent to learn autonomously and continuously, from on-going experience in the world, w...

This article explicates the interaction between implicit and explicit processes in skill learning, in contrast to the tendency of researchers to study each type in isolation. It highlights various effects of the interaction on learning (including synergy effects). The authors argue for an integrated model of skill learning that takes into account both implicit and explicit processes. Moreover, they argue for a bottom-up approach (first learning implicit knowledge and then explicit knowledge) in the integrated model. A variety of qualitative data can be accounted for by the approach. A computational model, CLARION, is then used to simulate a range of quantitative data. The results demonstrate the plausibility of the model, which provides a new perspective on skill learning. The role of implicit learning in skill acquisition and the distinction between implicit and explicit learning have been widely recognized in recent years (see, e.g., Cleeremans, Destrebecqz, &

This paper is an attempt at understanding the issue of consciousness through investigating its functional role, especially in learning, and through devising hybrid neural network models that (in a qualitative manner) approximate characteristics of human consciousness. In so doing, the paper examines explicit and implicit learning in a variety of psychological experiments and delineates the conscious/unconscious distinction in terms of the two types of learning and their respective products. The distinctions are captured in a two-level action-based model Clarion. Some fundamental theoretical issues are also clarified with the help of the model. Comparisons with existing models of consciousness are made to accentuate the present approach. KEYWORDS: Neural networks, hybrid systems, consciousness, implicit learning, reinforcement learning, procedural knowledge, rule extraction, dual representation 1 INTRODUCTION 3 1 Introduction Amidst the widespread enthusiasm of recent years concerning...

this article, we have presented evidence that a computational model that instantiates approximate, local learning with graded transfer provides a good account of how subjects learn on-line from outcome feedback in the SPF, a simple dynamic task. We base this conclusion on the model's ability to predict subjects' performance during training and on two subsequent tests of their ability to generalize, the control questions and the transfer task. We now explore the limitations of our efforts and discuss two alternative approaches to understanding human performance before concluding on our own approach 's merits

Two experiments examined the claim for distinct implicit and explicit learning modes in the artificial grammar-learning task (Reber, 1967, 1989). Subjects initially attempted to memorize strings of letters generated by a finite-state grammar and then classified new grammatical and nongrammatical strings. Experiment 1 showed that subjects ' assessment of isolated parts of strings was sufficient to account for their classification performance but that the rules elicited in free report were not sufficient. Experiment 2 showed that performing a concurrent random number generation task under different priorities interfered with free report and classification performance equally. Furthermore, giving different groups of subjects incidental or intentional learning instructions did not affect classification or free report. There appear to be many examples in everyday life of people learning to respond appropriately according to criteria that can readily state, for example, in learning the rules of algebra. This, however, is not always so. There also appear to be cases of people learning to respond in some rnlelike way without being able to say what the rules are that govern their

This paper argues for an explanation of the mechanistic (computational) basis of consciousness that is based on the distinction between localist (symbolic) representation and distributed representation, the ideas of which have been put forth in the connectionist literature. A model is developed to substantiate and test this approach. The paper also explores the issue of the functional roles of consciousness, in relation to the proposed mechanistic explanation of consciousness. The model, embodying the representational difference, is able to account for the functional role of consciousness, in the form of the synergy between the conscious and the unconscious. The fit between the model and various cognitive phenomena and data (documented in the psychological literatures) is discussed to accentuate the plausibility of the model and its explanation of consciousness. Comparisons with existing models of consciousness are made in the end.

The relationship between implicit memory and implicit learning is explored. Dienes and Fahey (1995) showed that learning to control a dynamic system was mediated by a look-up table consisting of previously successful responses to specific situations. The experiment reported in this paper showed that facilitated performance on old situations was independent of the subjects' ability to recognize those situations as old, suggesting that memory was implicit. Further analyses of the Dienes and Fahey data replicated this independence of control performance on recognition. However, unlike the implicit memory revealed on fragment completion tasks, successful performance on the dynamic control tasks was remarkably resilient to modality shifts. The results are discussed in terms of models of implicit learning and the nature of implicit memory.

Comparing the sensitivity of similar direct and indirect measures is proposed as the best way to provide evidence for unconscious learning. The authors apply this approach, first proposed by E. M. Reingold and P. M. Merikle (1988), to a choice reaction-time task in which the material is generated probabilistically on the basis of a finite-state grammar (A. Cleeremans, 1993). The data show that participants can learn about the structure of the stimulus material over training with the choice reaction-time task, but only to a limited extent—a result that is well predicted by the simple recurrent network model of A. Cleeremans and J. L. McClelland (1991). Participants can also use some of this knowledge to perform a subsequent generation task. However, detailed partial correlational analyses that control for knowledge as assessed by the generation task show that large effects of sequence learning are exclusively expressed through reaction time. This result suggests that at least some of this learning cannot be characterized as conscious. Over the last 10 years, interest in human learning has steadily increased, thanks in part to the development of connectionism and to renewed attention to the cognitive unconscious (Reber, 1993). Indeed, there is now a large body