Book Volume 1778 2000

Hybrid Neural Systems


ISBN: 978-3-540-67305-7 (Print) 978-3-540-46417-4 (Online)

Table of contents (27 chapters)

previous Page of 2
  1. Front Matter

    Pages -

  2. An Overview of Hybrid Neural Systems

    1. Chapter

      Pages 1-13

      An Overview of Hybrid Neural Systems

  3. Structured Connectionism and Rule Representation

    1. Chapter

      Pages 14-27

      Layered Hybrid Connectionist Models for Cognitive Science

    2. Chapter

      Pages 28-45

      Types and Quantifiers in SHRUTI – A Connectionist Model of Rapid Reasoning and Relational Processing

    3. Chapter

      Pages 46-62

      A Recursive Neural Network for Reflexive Reasoning

    4. Chapter

      Pages 63-77

      A Novel Modular Neural Architecture for Rule-Based and Similarity-Based Reasoning

    5. Chapter

      Pages 78-91

      Addressing Knowledge-Representation Issues in Connectionist Symbolic Rule Encoding for General Inference

    6. Chapter

      Pages 92-106

      Towards a Hybrid Model of First-Order Theory Refinement

  4. Distributed Neural Architectures and Language Processing

    1. Chapter

      Pages 107-122

      Dynamical Recurrent Networks for Sequential Data Processing

    2. Chapter

      Pages 123-143

      Fuzzy Knowledge and Recurrent Neural Networks: A Dynamical Systems Perspective

    3. Chapter

      Pages 144-157

      Combining Maps and Distributed Representations for Shift-Reduce Parsing

    4. Chapter

      Pages 158-174

      Towards Hybrid Neural Learning Internet Agents

    5. Chapter

      Pages 175-193

      A Connectionist Simulation of the Empirical Acquisition of Grammatical Relations

    6. Chapter

      Pages 194-203

      Large Patterns Make Great Symbols: An Example of Learning from Example

    7. Chapter

      Pages 204-210

      Context Vectors: A Step Toward a “Grand Unified Representation”

    8. Chapter

      Pages 211-225

      Integration of Graphical Rules with Adaptive Learning of Structured Information

  5. Transformation and Explanation

    1. Chapter

      Pages 226-239

      Lessons from Past, Current Issues, and Future Research Directions in Extracting the Knowledge Embedded in Artificial Neural Networks

    2. Chapter

      Pages 240-254

      Symbolic Rule Extraction from the DIMLP Neural Network

    3. Chapter

      Pages 255-269

      Understanding State Space Organization in Recurrent Neural Networks with Iterative Function Systems Dynamics

    4. Chapter

      Pages 270-285

      Direct Explanations and Knowledge Extraction from a Multilayer Perceptron Network that Performs Low Back Pain Classification

    5. Chapter

      Pages 286-297

      High Order Eigentensors as Symbolic Rules in Competitive Learning

previous Page of 2