Turing's connectionism provides a detailed and in-depth analysis of Turing's almost forgotten ideas on connectionist machines. In a little known paper entitled "Intelligent Machinery", Turing already investigated connectionist models as early as 1948. Unfortunately, his work was dismissed by his employer as a "schoolboy essay" and went unpublished until 1968, 14 years after his death. In this book, Christof Teuscher analyzes all aspects of Turing's "unorganized machines". Turing himself also proposed a sort of genetic algorithm to train the networks. This idea has been resumed by the author and genetic algorithms are used to build and train Turing's unorganized machines. Teuscher's work starts from Turing's initial ideas, but importantly goes beyond them. Many new kinds of machines and new aspects are considered, e.g., hardware implementation, analysis of the complex dynamics of the networks, hypercomputation, and learning algorithms.
Contains a Foreword by B. Jack Copeland and D. Proudfoot
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.