Deep Fusion of Computational and Symbolic Processing

1. Front Matter

   Pages I-XIV

   PDF

2. Integration of Computational and Symbolic Processing

   1. Front Matter

      Pages 1-1

      PDF

   2. A Subsymbolic and Symbolic Model for Learning Sequential Decision Tasks

      • Ron Sun, Todd Peterson

      Pages 3-20

   3. Integration of Different Information Processing Methods

      • Setsuo Ohsuga

      Pages 21-40

   4. Symbol Pattern Integration Using Multilinear Functions

      • Pattern Reasoning

      Pages 41-70

3. Toward Deep Fusion of Computational and Symbolic Processing

   1. Front Matter

      Pages 71-71

      PDF

   2. Design of Autonomously Learning Controllers Using Fynesse

      • Ralf Schoknecht, Martin Spott, Martin Riedmiller

      Pages 73-103

   3. Modeling for Dynamic Systems with Fuzzy Sequential Knowledge

      • I. Takeuchi, T. Furuhashi

      Pages 104-120

   4. Hybrid Machine Learning Tools: INSS — A Neuro-Symbolic System for Constructive Machine Learning

      • Fernando Osório, Bernard Amy, Adelmo Cechin

      Pages 121-144

   5. A Generic Architecture for Hybrid Intelligent Systems

      • Hans-Arno Jacobsen

      Pages 145-172

   6. New Paradigm toward Deep Fusion of Computational and Symbolic Processing

      • Shun’ichi Tano

      Pages 173-197

4. Knowledge Representation

   1. Front Matter

      Pages 199-199

      PDF

   2. Fusion of Symbolic and Quantitative Processing by Conceptual Fuzzy Sets

      • Tomohiro Takagi

      Pages 201-219

   3. Novel Knowledge Representation (Area Representation) and the Implementation by Neural Network

      • Masafumi Hagiwara, Naruhiro Ikeda

      Pages 220-237

   4. A Symbol Grounding Problem of Gesture Motion through a Self-organizing Network of Time-varying Motion Images

      • Toshiro Mukai, Takuichi Nishimura, Takashi Endo, Ryuichi Oka

      Pages 238-250

5. Back Matter

   Pages 251-257

   PDF

Symbolic processing has limitations highlighted by the symbol grounding problem. Computational processing methods, like fuzzy logic, neural networks, and statistical methods have appeared to overcome these problems. However, they also suffer from drawbacks in that, for example, multi-stage inference is difficult to implement. Deep fusion of symbolic and computational processing is expected to open a new paradigm for intelligent systems. Symbolic processing and computational processing should interact at all abstract or computational levels. For this undertaking, attempts to combine, hybridize, and fuse these processing methods should be thoroughly investigated and the direction of novel fusion approaches should be clarified. This book contains the current status of this attempt and also discusses future directions.

• Computational Processing
• Neuro-symbolic System
• Symbolic Processing
• control
• dynamical systems
• fuzzy logic
• fuzzy sets
• information processing
• intelligence
• knowledge representation
• learning
• logic
• machine learning
• modeling
• neural networks

• Department of Information and Electronics, Nagoya University, Nagoya, Japan

  Takeshi Furuhashi

• Graduate School of Information Systems, University of Electro-Communications, Choufu, Japan

  Shun’Ichi Tano

• Project CARAVEL, INRIA-Rocquencourt, Le Chesnay Cedex, France

  Hans-Arno Jacobsen

Policies and ethics