Turing's connectionism : an investigation of neural network architectures
著者
書誌事項
Turing's connectionism : an investigation of neural network architectures
（Discrete mathematics and theoretical computer science）
Springer-Verlag, c2002
大学図書館所蔵 件 / 全6件
-
該当する所蔵館はありません
- すべての絞り込み条件を解除する
注記
Includes bibliographical references (p. [187]-196) and index
内容説明・目次
内容説明
Christof Teuscher revives, analyzes, and simulates Turing's ideas, applying them to different types of problems, and building and training Turing's machines using evolutionary algorithms. In a little known paper entitled 'Intelligent Machinery' Turing investigated connectionist networks, but his work was dismissed as a 'schoolboy essay'and it was left unpublished until 1968, 14 years after his death. This is not a book about today's (classical) neural networks, but about the neuron network-like structures proposed by Turing. One of its novel features is that it actually goes beyond Turing's ideas by proposing new machines. The book also contains a Foreward by B. Jack Copeland and D. Proudfoot.
目次
Foreword by B.J. Copeland and D. Proudfoot.- INTRODUCTION: Turing's Anticipation of Connectionism. Alan Mathison Turing. Connectionism and Artificial Neural Networks. Historical Context and Related Work. Organization of the Book. Book Web-Site.- INTELLIGENT MACHINERY: Machines. Turing's Unorganized Machines. Formalization and Analysis of Unorganized Machines. New Unorganized Machines. Simulation of TBI-type Machines with MATLAB.- SYNTHESIS OF LOGICAL FUNCTIONS AND DIGITAL SYSTEMS WITH TURING NETWORKS: Combinational versus Sequential Systems. Synthesis of Logical Functions with A-type Networks. Synthesis of Logical Functions with TB-type Networks. Multiplexer and Demultiplexer. Delay-Unit. Shift-Register. How to Design Complex Systems. Hardware Implementation.- ORGANIZING UNORGANIZED MACHINES: Evolutionary Algorithms. Evolutionary Artificial Neural Networks. Example: Evolve Networks that Regenerate Bitstreams. Signal Processing in Turing Networks. Pattern Classification. Examples: Pattern Classification with Genetic Algorithms. A Learning Algorithm for Turing Networks.- NETWORK PROPERTIES AND CHARACTERISTICS: General Properties. Computational Power. State Machines. Threshold Logic. Dynamical Systems and the State-Space Model. Random Boolean Networks. Attractors. Network Stability and Activity. Chaos, Bifurcation, and Self-Organized Criticality. Topological Evolution and Self-Organization. Hypercomputation: Computing Beyond the Turing Limit with Turing's Neural Networks?- EPILOGUE.
「Nielsen BookData」 より
