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.

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 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.

We propose that humans are adapted to transfer knowledge to, and receive knowledge from, conspecifics by teaching. This adaptation, which we call 'pedagogy', involves the emergence of a special communication system that does not presuppose either language or high-level theory of mind, but could itself provide a basis facilitating the development of these human-specific abilities both in phylogenetic and ontogenetic terms. We speculate that tool manufacturing and mediated tool use made the evolution of such a new social learning mechanism necessary. However, the main body of evidence supporting this hypothesis comes from developmental psychology. We argue that many central phenomena of human infant social cognition that may seem puzzling in the light of their standard functional explanation can be more coherently and plausibly interpreted as reflecting the adaptations to receive knowledge from social partners through teaching.

ABSTRACT This article addresses issues in developing cognitive architectures—generic computational models of cognition. Cognitive architectures are believed to be essential in advancing understanding of the mind, and therefore, developing cognitive architectures is an extremely important enterprise in cognitive science. The article proposes a set of essential desiderata for developing cognitive architectures. It then moves on to discuss in detail some of these desiderata and their associated concepts and ideas relevant to developing better cognitive architectures. It argues for the importance of taking into full consideration these desiderata in developing future architectures that are more cognitively and ecologically realistic. A brief and preliminary evaluation of existing cognitive architectures is attempted on the basis of these ideas. 1.

This paper explores the interaction between implicit and explicit processes during skill learning, in terms of top-down learning (that is, learning that goes from explicit to implicit knowledge) versus bottom-up learning (that is, learning that goes from implicit to explicit knowledge). Instead of studying each type of knowledge (implicit or explicit) in isolation, we stress the interaction between the two types, especially in terms of one type giving rise to the other, and its e#ects on learning. The work presents an integrated model of skill learning that takes into account both implicit and explicit processes and both top-down and bottom-up learning. We examine and simulate human data in the Tower of Hanoi task. The paper shows how the quantitative data in this task may be captured using either top-down or bottom-up approaches, although top-down learning is a more apt explanation of the human data currently available. These results illustrate the two different directions of learning (top-down versus bottom-up), and thereby provide a new perspective on skill learning.

The interactivist approach to development generates a framework of types of constraints on what can be constructed. The four constraint types are based on: (1) what the constructed systems are about; (2) the representational relationship itself; (3) the nature of the systems being constructed; and (4) the process of construction itself. We give illustrations of each constraint type. Any developmental theory needs to acknowledge all four types of constraint; however, some current theories conflate different types of constraint, or rely on a single constraint type to explicate development. Such theories will be inherently unable to explain important aspects of development.

This paper explicates the interaction between the implicit and explicit learning processes in skill acquisition, contrary to the common tendency in the literature of studying each type of learning in isolation. It highlights the interaction between the two types of processes and its various effects on learning, including the synergy effect. This work advocates an integrated model of skill learning that takes into account both implicit and explicit processes; moreover, it embodies a bottom-up approach (first learning implicit knowledge and then explicit knowledge on its basis) towards skill learning. The paper shows that this approach accounts for various effects in the process control task data, in addition to accounting for other data reported elsewhere.

Many attempts have been made to capture the very nature of knowledge in different fields: philosophy, cognitive science, artificial intelligence, etc. There is now a renewal of the studies on context and several proposals to represent and implement the context in "intelligent" systems. Up to now, there were, as far as we know, few attempts to compare the two concepts of context and knowledge, while they obviously share some common aspects. In this paper, we review the main characteristics of both concepts and, while we note a large overlapping of the two concepts, we also emphasize their differences as regards decision making and action.