ISBN-10:
354073953X
ISBN-13:
9783540739531
Pub. Date:
11/09/2007
Publisher:
Springer Berlin Heidelberg
Perspectives of Neural-Symbolic Integration / Edition 1

Perspectives of Neural-Symbolic Integration / Edition 1

by Barbara Hammer, Pascal Hitzler

Hardcover

Current price is , Original price is $279.99. You

Temporarily Out of Stock Online

Please check back later for updated availability.

Overview

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.

Product Details

ISBN-13: 9783540739531
Publisher: Springer Berlin Heidelberg
Publication date: 11/09/2007
Series: Studies in Computational Intelligence , #77
Edition description: 2007
Pages: 319
Product dimensions: 6.10(w) x 9.25(h) x 0.03(d)

Table of Contents

Preface     IX
Structured Data and Neural Networks
Introduction: Structured Data and Neural Networks     3
Kernels for Strings and Graphs   Craig Saunders   Anthony Demco     7
Comparing Sequence Classification Algorithms for Protein Subcellular Localization   Fabrizio Costa   Sauro Menchetti   Paolo Frasconi     23
Mining Structure-Activity Relations in Biological Neural Networks using NeuronRank   Tayfun Gurel   Luc De Raedt   Stefan Rotter     49
Adaptive Contextual Processing of Structured Data by Recursive Neural Networks: A Survey of Computational Properties   Barbara Hammer   Alessio Micheli   Alessandro Sperduti     67
Markovian Bias of Neural-based Architectures With Feedback Connections   Peter Tino   Barbara Hammer   Mikael Boden     95
Time Series Prediction with the Self-Organizing Map: A Review   Guilherme A. Barreto     135
A Dual Interaction Perspective for Robot Cognition: Grasping as a "Rosetta Stone"   Helge Ritter   Robert Haschke   Jochen J. Steil     159
Logic and Neural Networks
Introduction: Logic and Neural Networks     181
SHRUTI: A Neurally Motivated Architecture for Rapid, ScalableInference   Lokendra Shastri     183
The Core Method: Connectionist Model Generation for First-Order Logic Programs   Sebastian Bader   Pascal Hitzler   Steffen Holldobler   Andreas Witzel     205
Learning Models of Predicate Logical Theories with Neural Networks Based on Topos Theory   Helmar Gust   Kai-Uwe Kuhnberger   Peter Geibel     233
Advances in Neural-Symbolic Learning Systems: Modal and Temporal Reasoning   Artur S. d'Avila Garcez     265
Connectionist Representation of Multi-Valued Logic Programs   Ekaterina Komendantskaya   Maire Lane   Anthony Karel Seda     283
Index     315

Customer Reviews

Most Helpful Customer Reviews

See All Customer Reviews