From Synapses to Rules

Discovering Symbolic Rules from Neural Processed Data

  • Bruno Apolloni
  • Franz Kurfess

Table of contents

  1. Front Matter
    Pages i-xxiii
  2. The Theoretical Bases of Learning

    1. Front Matter
      Pages 1-4
    2. Bruno Apolloni, Simone Bassis, Sabrina Gaito, Dario Malchiodi
      Pages 5-40
    3. Bruno Apolloni, Stefano Baraghini, Giorgio Palmas
      Pages 41-60
    4. Bruno Apolloni, Sabrina Gaito, Domenico Iannizzi, Dario Malchiodi
      Pages 61-73
    5. Bruno Apolloni, Simone Bassis, Sabrina Gaito, Dario Malchiodi
      Pages 75-86
    6. Bruno Apolloni, Dario Malchiodi, Christos Orovas, Anna Maria Zanaboni
      Pages 117-128
  3. Physical Aspects of Learning

    1. Front Matter
      Pages 135-137
    2. Gabriele E. M. Biella
      Pages 139-164
    3. L. F. Agnati, L. M. Santarossa, F. Benfenati, M. Ferri, A. Morpurgo, B. Apolloni et al.
      Pages 165-195
    4. Bruno Apolloni, Sabrina Gaito, Dario Malchiodi
      Pages 251-260
  4. Systems that Bridge the Gap

  5. Back Matter
    Pages 385-388

About this book


One high-level ability of the human brain is to understand what it has learned. This seems to be the crucial advantage in comparison to the brain activity of other primates. At present we are technologically almost ready to artificially reproduce human brain tissue, but we still do not fully understand the information processing and the related biological mechanisms underlying this ability. Thus an electronic clone of the human brain is still far from being realizable. At the same time, around twenty years after the revival of the connectionist paradigm, we are not yet satisfied with the typical subsymbolic attitude of devices like neural networks: we can make them learn to solve even difficult problems, but without a clear explanation of why a solution works. Indeed, to widely use these devices in a reliable and non elementary way we need formal and understandable expressions of the learnt functions. of being tested, manipulated and composed with These must be susceptible other similar expressions to build more structured functions as a solution of complex problems via the usual deductive methods of the Artificial Intelligence. Many effort have been steered in this directions in the last years, constructing artificial hybrid systems where a cooperation between the sub symbolic processing of the neural networks merges in various modes with symbolic algorithms. In parallel, neurobiology research keeps on supplying more and more detailed explanations of the low-level phenomena responsible for mental processes.


Nervous System algorithms artificial intelligence fuzzy intelligence knowledge learning modeling neural network

Editors and affiliations

  • Bruno Apolloni
    • 1
  • Franz Kurfess
    • 2
  1. 1.Department of Information ScienceUniversity of MilanMilanItaly
  2. 2.Department of Computer ScienceCalifornia Polytechnic State UniversitySan Luis ObispoUSA

Bibliographic information

  • DOI
  • Copyright Information Kluwer Academic/Plenum Publishers, New York 2002
  • Publisher Name Springer, Boston, MA
  • eBook Packages Springer Book Archive
  • Print ISBN 978-1-4613-5204-4
  • Online ISBN 978-1-4615-0705-5
  • Buy this book on publisher's site
Industry Sectors
Chemical Manufacturing
Finance, Business & Banking
IT & Software
Energy, Utilities & Environment