Learning in Natural and Connectionist Systems

1. Front Matter

   Pages i-xvi

   PDF

2. Introduction

   • R. Hans Phaf

   Pages 1-20

3. A connectionist approach to learning

   • R. Hans Phaf

   Pages 21-95

4. Psychological constraints on learning

   • R. Hans Phaf

   Pages 96-179

5. A connectionist model for implicit and explicit memory

   • R. Hans Phaf

   Pages 180-244

6. Evaluation

   • R. Hans Phaf

   Pages 245-264

7. Back Matter

   Pages 265-294

   PDF

Modern research in neural networks has led to powerful artificial learning systems, while recent work in the psychology of human memory has revealed much about how natural systems really learn, including the role of unconscious, implicit, memory processes. Regrettably, the two approaches typically ignore each other. This book, combining the approaches, should contribute to their mutual benefit.
New empirical work is presented showing dissociations between implicit and explicit memory performance. Recently proposed explanations for such data lead to a new connectionist learning procedure: CALM (Categorizing and Learning Module), which can learn with or without supervision, and shows practical advantages over many existing procedures. Specific experiments are simulated by a network model (ELAN) composed of CALM modules. A working memory extension to the model is also discussed that could give it symbol manipulation abilities.
The book will be of interest to memory psychologists and connectionists, as well as to cognitive scientists who in the past have tended to restrict themselves to symbolic models.

• evaluation
• learning systems
• neural networks

• Psychonomics Department, University of Amsterdam, Amsterdam, The Netherlands

  R. Hans Phaf

Policies and ethics