On the Construction of Artificial Brains

  • Ulrich Ramacher
  • Christoph von der Malsburg

Table of contents

  1. Front Matter
  2. Ulrich Ramacher, Christoph von der Malsburg
    Pages 1-9
  3. Ulrich Ramacher, Christoph von der Malsburg
    Pages 11-19
  4. Ulrich Ramacher, Christoph von der Malsburg
    Pages 21-45
  5. Ulrich Ramacher, Christoph von der Malsburg
    Pages 47-58
  6. Ulrich Ramacher, Christoph von der Malsburg
    Pages 59-81
  7. Ulrich Ramacher, Christoph von der Malsburg
    Pages 83-104
  8. Ulrich Ramacher, Christoph von der Malsburg
    Pages 105-118
  9. Ulrich Ramacher, Christoph von der Malsburg
    Pages 119-139
  10. Ulrich Ramacher, Christoph von der Malsburg
    Pages 141-148
  11. Ulrich Ramacher, Christoph von der Malsburg
    Pages 149-171
  12. Ulrich Ramacher, Christoph von der Malsburg
    Pages 173-182
  13. Ulrich Ramacher, Christoph von der Malsburg
    Pages 183-194
  14. Ulrich Ramacher, Christoph von der Malsburg
    Pages 195-231
  15. Ulrich Ramacher, Christoph von der Malsburg
    Pages 233-246
  16. Ulrich Ramacher, Christoph von der Malsburg
    Pages 247-254
  17. Ulrich Ramacher, Christoph von der Malsburg
    Pages 255-267
  18. Ulrich Ramacher, Christoph von der Malsburg
    Pages 269-298
  19. Ulrich Ramacher, Christoph von der Malsburg
    Pages 299-323
  20. End
    Ulrich Ramacher, Christoph von der Malsburg
    Pages 325-326

About this book

Introduction

This book presents a first generation of artificial brains, using vision as sample application. An object recognition system is built, using neurons and synapses as exclusive building elements. The system contains a feature pyramid with 8 orientations and 5 resolution levels for 1000 objects and networks for binding of features into objects. This vision system can recognize objects robustly in the presence of changes in illumination, deformation, distance and pose (as long as object components remain visible).

The neuro-synaptic network owes its functional power to the introduction of rapidly modifiable dynamic synapses. These give a network greater pattern recognition capabilities than are achievable with fixed connections. The spatio-temporal correlation structure of patterns is captured by a single synaptic differential equation in a universal way. The correlation can appear as synchronous neural firing, which signals the presence of a feature in a robust way, or binds features into objects.

Although in this book we can present only a first generation artificial brain and believe many more generations will have to follow to reach the full power of the human brain, we nevertheless see a new era of computation on the horizon. There were times when computers, with their precision, reliability and blinding speed, were considered to be as superior to the wet matter of our brain as a jet plane is to a sparrow. These times seem to be over, given the fact that digital systems inspired by formal logic and controlled algorithmically - today's computers - are hitting a complexity crisis. A paradigm change is in the air: from the externally organised to the self-organised computer, of which the results described in this book may give an inkling.

Keywords

Extension Prolog Sensor cognition complexity control deformation formal logic information processing logic modeling neurons object recognition pattern recognition simulation

Authors and affiliations

  • Ulrich Ramacher
    • 1
  • Christoph von der Malsburg
    • 2
  1. 1.Head of System EngineeringCOM SDR, Infineon Technologies AGMunichGermany
  2. 2.Frankfurt Institute for Advanced StudiesFrankfurt a. M.Germany

Bibliographic information

  • DOI https://doi.org/10.1007/978-3-642-00189-5
  • Copyright Information Springer-Verlag Berlin Heidelberg 2010
  • Publisher Name Springer, Berlin, Heidelberg
  • eBook Packages Physics and Astronomy
  • Print ISBN 978-3-642-00188-8
  • Online ISBN 978-3-642-00189-5
  • About this book