Studies in Computational Intelligence

Perspectives of Neural-Symbolic Integration

Editors: Hammer, Barbara, Hitzler, Pascal (Eds.)

  • An essential text that details recent developments in neural-symbolic integration
  • With contributions from leading researchers in the field
  • Covers theoretical foundations as well as algorithmic design
see more benefits

Buy this book

eBook $189.00
price for USA (gross)
valid through November 5, 2017
  • ISBN 978-3-540-73954-8
  • Digitally watermarked, DRM-free
  • Included format: PDF
  • ebooks can be used on all reading devices
  • Immediate eBook download after purchase
Hardcover $249.00
price for USA
valid through November 5, 2017
  • ISBN 978-3-540-73953-1
  • Free shipping for individuals worldwide
  • Usually dispatched within 3 to 5 business days.
Softcover $249.00
price for USA
valid through November 5, 2017
  • ISBN 978-3-642-09322-7
  • Free shipping for individuals worldwide
  • Usually dispatched within 3 to 5 business days.
About this book

The human brain possesses the remarkable capability of understanding, interpreting, and producing language, structures, and logic. Unlike their biological counterparts, artificial neural networks do not form such a close liason with symbolic reasoning: logic-based inference mechanisms and statistical machine learning constitute two major and very different paradigms in artificial intelligence with complementary strengths and weaknesses. Modern application scenarios in robotics, bioinformatics, language processing, etc., however require both the efficiency and noise-tolerance of statistical models and the generalization ability and high-level modelling of structural inference meachanisms. A variety of approaches has therefore been proposed for combining the two paradigms.

This carefully edited volume contains state-of-the-art contributions in neural-symbolic integration, covering `loose' coupling by means of structure kernels or recursive models as well as `strong' coupling of logic and neural networks. It brings together a representative selection of results presented by some of the top researchers in the field, covering theoretical foundations, algorithmic design, and state-of-the-art applications in robotics and bioinformatics.

Table of contents (12 chapters)

  • Kernels for Strings and Graphs

    Saunders, Craig (et al.)

    Pages 7-22

  • Comparing Sequence Classification Algorithms for Protein Subcellular Localization

    Costa, Fabrizio (et al.)

    Pages 23-48

  • Mining Structure-Activity Relations in Biological Neural Networks using NeuronRank

    Gürel, Tayfun (et al.)

    Pages 49-65

  • Adaptive Contextual Processing of Structured Data by Recursive Neural Networks: A Survey of Computational Properties

    Hammer, Barbara (et al.)

    Pages 67-94

  • Markovian Bias of Neural-based Architectures With Feedback Connections

    Tiňo, Peter (et al.)

    Pages 95-133

Buy this book

eBook $189.00
price for USA (gross)
valid through November 5, 2017
  • ISBN 978-3-540-73954-8
  • Digitally watermarked, DRM-free
  • Included format: PDF
  • ebooks can be used on all reading devices
  • Immediate eBook download after purchase
Hardcover $249.00
price for USA
valid through November 5, 2017
  • ISBN 978-3-540-73953-1
  • Free shipping for individuals worldwide
  • Usually dispatched within 3 to 5 business days.
Softcover $249.00
price for USA
valid through November 5, 2017
  • ISBN 978-3-642-09322-7
  • Free shipping for individuals worldwide
  • Usually dispatched within 3 to 5 business days.
Loading...

Recommended for you

Loading...

Bibliographic Information

Bibliographic Information
Book Title
Perspectives of Neural-Symbolic Integration
Editors
  • Barbara Hammer
  • Pascal Hitzler
Series Title
Studies in Computational Intelligence
Series Volume
77
Copyright
2007
Publisher
Springer-Verlag Berlin Heidelberg
Copyright Holder
Springer-Verlag Berlin Heidelberg
eBook ISBN
978-3-540-73954-8
DOI
10.1007/978-3-540-73954-8
Hardcover ISBN
978-3-540-73953-1
Softcover ISBN
978-3-642-09322-7
Series ISSN
1860-949X
Edition Number
1
Number of Pages
XIII, 319
Topics