E-raamat: Turing's Connectionism: An Investigation of Neural Network Architectures

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Machinery' Turing investigated connectionist networks, but his work was dismissed as a 'schoolboy essay'and it was left unpublished until 1968, 14 years after his death.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.

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 Unfortunately, his work was dismissed by his employer as a "schoolboy essay" and went unpublished until 1968, 14 years after his death.In this book, Christof Teuscher analyzes all aspects of Turing's "unorganized machines".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.