Computational Architectures Integrating Neural and Symbolic Processes

A Perspective on the State of the Art
1995
ISBN: 978-0-7923-9517-1
Verlag: Springer US

Buch, Englisch, Band 292, 476 Seiten, HC runder Rücken kaschiert, Format (B × H): 160 mm x 241 mm, Gewicht: 1930 g

Reihe: The Springer International Series in Engineering and Computer Science

focuses on a currently emerging body of research. With the reemergence of neural networks in the 1980s with their emphasis on overcoming some of the limitations of symbolic AI, there is clearly a need to support some form of high-level symbolic processing in connectionist networks. As argued by many researchers, on both the symbolic AI and connectionist sides, many cognitive tasks, e.g. language understanding and common sense reasoning, seem to require high-level symbolic capabilities. How these capabilities are realized in connectionist networks is a difficult question and it constitutes the focus of this book.
addresses the underlying architectural aspects of the integration of neural and symbolic processes. In order to provide a basis for a deeper understanding of existing divergent approaches and provide insight for further developments in this field, this book presents: (1) an examination of specific architectures (grouped together according to their approaches), their strengths and weaknesses, why they work, and what they predict, and (2) a critique/comparison of these approaches.
is of interest to researchers, graduate students, and interested laymen, in areas such as cognitive science, artificial intelligence, computer science, cognitive psychology, and neurocomputing, in keeping up-to-date with the newest research trends. It is a comprehensive, in-depth introduction to this new emerging field.

Zielgruppe

Research

Autoren/Hrsg.

Bookman, Lawrence A.

Sun, Ron

Fachgebiete

• Mathematik | Informatik EDV | Informatik Informatik Künstliche Intelligenz Wissensbasierte Systeme, Expertensysteme
• Naturwissenschaften Biowissenschaften Biowissenschaften Neurobiologie, Verhaltensbiologie
• Naturwissenschaften Physik Angewandte Physik Statistische Physik, Dynamische Systeme
• Mathematik | Informatik EDV | Informatik EDV & Informatik Allgemein
• Technische Wissenschaften Elektronik | Nachrichtentechnik Elektronik Robotik
• Mathematik | Informatik EDV | Informatik Informatik Künstliche Intelligenz Maschinelles Lernen

Inhaltsverzeichnis

Parallelism in inheritance hierarchies with exceptions.- An Introduction: On Symbolic Processing in Neural Networks.- Localist Architectures.- Complex Symbol-Processing in Conposit, A Transiently Localist Connectionist Architecture.- A Structured Connectionist Approach to Inferencing and Retrieval.- Hierarchical Architectures for Reasoning.- Distributed Architectures.- Subsymbolic Parsing of Embedded Structures.- Towards Instructable Connectionist Systems.- An Internal Report for Connectionists.- Combined Architectures.- A Two-Level Hybrid Architecture for Structuring Knowledge for Commonsense Reasoning.- A Framework for Integrating Relational and Associational Knowledge for Comprehension.- Examining a Hybrid Connectionist/Symbolic System for the Analysis of Ballistic Signals.- Commentaries.- Symbolic Artificial Intelligence and Numeric Artificial Neural Networks: Towards a Resolution of the Dichotomy.- Connectionist Natural Language Processing: A Status Report.