Deep Fusion of Computational and Symbolic Processing

• Corporate Author: SpringerLink (Online service)
• Other Authors: Furuhashi, Takeshi (Editor, http://id.loc.gov/vocabulary/relators/edt), Tano, Shun'Ichi (Editor, http://id.loc.gov/vocabulary/relators/edt), Jacobsen, Hans-Arno (Editor, http://id.loc.gov/vocabulary/relators/edt)
• Format: Electronic eBook
• Language: English
• Published: Heidelberg : Physica-Verlag HD : Imprint: Physica, 2001.
• Edition: 1st ed. 2001.
• Series: Studies in Fuzziness and Soft Computing, 59
• Subjects: Computer programming.; Artificial intelligence.; Programming Techniques.; Artificial Intelligence.

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...

Table of Contents:

• I. Integration of Computational and Symbolic Processing
• A Subsymbolic and Symbolic Model for Learning Sequential Decision Tasks
• Integration of Different Information Processing Methods
• Symbol Pattern Integration Using Multilinear Functions
• II. Toward Deep Fusion of Computational and Symbolic Processing
• Design of Autonomously Learning Controllers Using FYNESSE
• Modeling for Dynamical Systems with Fuzzy Sequential Knowledge
• Hybrid Machine Learning Tools: INSS - A Neuro-Symbolic System for Constructive Machine Learning
• A Generic Architecture for Hybrid Intelligent Systems
• New Paradigm toward Deep Fusion of Computational and Symbolic Processing
• III. Knowledge Representation
• Fusion of Symbolic and Quantitative Processing by Conceptual Fuzzy Sets
• Novel Knowledge Representation (Area Representation) and the Implementation by Neural Network
• A Symbol Grounding Problem of Gesture Motion through a Self-organizing Network of Time-varying Motion Images.