Hybrid Neural Systems

✍ Scribed by Stefan Wermter, Ron Sun (auth.), Stefan Wermter, Ron Sun (eds.)

• Publisher: Springer-Verlag Berlin Heidelberg
• Year: 2000
• Tongue: English
• Leaves: 410
• Series: Lecture Notes in Computer Science 1778 : Lecture Notes in Artificial Intelligence
• Edition: 1
• Category: Library

✦ Synopsis

Hybrid neural systems are computational systems which are based mainly on artificial neural networks and allow for symbolic interpretation or interaction with symbolic components. This book is derived from a workshop held during the NIPS'98 in Denver, Colorado, USA, and competently reflects the state of the art of research and development in hybrid neural systems.
The 26 revised full papers presented together with an introductory overview by the volume editors have been through a twofold process of careful reviewing and revision. The papers are organized in the following topical sections: structured connectionism and rule representation; distributed neural architectures and language processing; transformation and explanation; robotics, vision, and cognitive approaches.

✦ Table of Contents

Front Matter....Pages -
An Overview of Hybrid Neural Systems....Pages 1-13
Layered Hybrid Connectionist Models for Cognitive Science....Pages 14-27
Types and Quantifiers in SHRUTI – A Connectionist Model of Rapid Reasoning and Relational Processing....Pages 28-45
A Recursive Neural Network for Reflexive Reasoning....Pages 46-62
A Novel Modular Neural Architecture for Rule-Based and Similarity-Based Reasoning....Pages 63-77
Addressing Knowledge-Representation Issues in Connectionist Symbolic Rule Encoding for General Inference....Pages 78-91
Towards a Hybrid Model of First-Order Theory Refinement....Pages 92-106
Dynamical Recurrent Networks for Sequential Data Processing....Pages 107-122
Fuzzy Knowledge and Recurrent Neural Networks: A Dynamical Systems Perspective....Pages 123-143
Combining Maps and Distributed Representations for Shift-Reduce Parsing....Pages 144-157
Towards Hybrid Neural Learning Internet Agents....Pages 158-174
A Connectionist Simulation of the Empirical Acquisition of Grammatical Relations....Pages 175-193
Large Patterns Make Great Symbols: An Example of Learning from Example....Pages 194-203
Context Vectors: A Step Toward a “Grand Unified Representation”....Pages 204-210
Integration of Graphical Rules with Adaptive Learning of Structured Information....Pages 211-225
Lessons from Past, Current Issues, and Future Research Directions in Extracting the Knowledge Embedded in Artificial Neural Networks....Pages 226-239
Symbolic Rule Extraction from the DIMLP Neural Network....Pages 240-254
Understanding State Space Organization in Recurrent Neural Networks with Iterative Function Systems Dynamics....Pages 255-269
Direct Explanations and Knowledge Extraction from a Multilayer Perceptron Network that Performs Low Back Pain Classification....Pages 270-285
High Order Eigentensors as Symbolic Rules in Competitive Learning....Pages 286-297
Holistic Symbol Processing and the Sequential RAAM: An Evaluation....Pages 298-312
Life, Mind, and Robots....Pages 313-332
Supplementing Neural Reinforcement Learning with Symbolic Methods....Pages 333-347
Self-Organizing Maps in Symbol Processing....Pages 348-362
Evolution of Symbolisation: Signposts to a Bridge between Connectionist and Symbolic Systems....Pages 363-371
A Cellular Neural Associative Array for Symbolic Vision....Pages 372-386
Application of Neurosymbolic Integration for Environment Modelling in Mobile Robots....Pages 387-401
Back Matter....Pages -

✦ Subjects

Artificial Intelligence (incl. Robotics); Computation by Abstract Devices; Processor Architectures; Neurosciences