Recruitment Learning

1. Front Matter

   PDF

2. Recruitment in Discrete-time Neural Networks

   1. Front Matter

      Pages 1-1

      PDF

   2. Recruitment Learning – An Introduction

      • Joachim Diederich, Cengiz Günay, James M. Hogan

      Pages 3-36

   3. One-Shot Learning – Specialization and Generalization

      • Joachim Diederich, Cengiz Günay, James M. Hogan

      Pages 37-56

   4. Connectivity and Candidate Structures

      • Joachim Diederich, Cengiz Günay, James M. Hogan

      Pages 57-81

   5. Representation and Recruitment

      • Joachim Diederich, Cengiz Günay, James M. Hogan

      Pages 83-135

   6. Cognitive Applications

      • Joachim Diederich, Cengiz Günay, James M. Hogan

      Pages 137-179

3. Recruitment in Continuous-time Neural Networks

   1. Front Matter

      Pages 181-181

      PDF

   2. Spiking Neural Networks and Temporal Binding

      • Joachim Diederich, Cengiz Günay, James M. Hogan

      Pages 183-198

   3. Synchronized Recruitment in Cortical Hierarchies

      • Joachim Diederich, Cengiz Günay, James M. Hogan

      Pages 199-242

   4. The Stability of Recruited Concepts

      • Joachim Diederich, Cengiz Günay, James M. Hogan

      Pages 243-274

   5. Conclusion

      • Joachim Diederich, Cengiz Günay, James M. Hogan

      Pages 275-281

4. Back Matter

   PDF

This book presents a fascinating and self-contained account of "recruitment learning", a model and theory of fast learning in the neocortex. In contrast to the more common attractor network paradigm for long- and short-term memory, recruitment learning focuses on one-shot learning or "chunking" of arbitrary feature conjunctions that co-occur in single presentations. The book starts with a comprehensive review of the historic background of recruitment learning, putting special emphasis on the ground-breaking work of D.O. Hebb, W.A.Wickelgren, J.A.Feldman, L.G.Valiant, and L. Shastri. Afterwards a thorough mathematical analysis of the model is presented which shows that recruitment is indeed a plausible mechanism of memory formation in the neocortex. A third part extends the main concepts towards state-of-the-art spiking neuron models and dynamic synchronization as a tentative solution of the binding problem. The book further discusses the possible role of adult neurogenesis for recruitment. These recent developments put the theory of recruitment learning at the forefront of research on biologically inspired memory models and make the book an important and timely contribution to the field.

• Computational Intelligence
• Recruitment Learning

• School of Information Technology and Electrical Engineering, School of Medicine - Central Clinical Division, The University of Queensland, Brisbane, Australia

  Joachim Diederich

• Department of Biology, Emory University, Atlanta, U.S.A.

  Cengiz Günay

• School of Software Engineering and Data Communications, Queensland University of Technology, Brisbane, Australia

  James M. Hogan

Policies and ethics