Talking Nets: An Oral History Of Neural Networks

Talking Nets: An Oral History of Neural Networks

ReviewTalking Nets is a fascinating book...Anyone with a serious -- or even half-serious -- interest in neural networks, or in the history of AI or cognitive science, should read Talking Nets. (Margaret A. Boden Times Literary Supplement)A fascinating compilation of discussions with many of the pioneers in neurocomputing. This book will certainly help fill in the motivations and historical context surrounding many of the fundamental breakthroughs in the area. (James L. McClelland, Center for the Neural Basis of Cognition)Since World War II, a group of scientists has been attempting to understand the human nervous system and to build computer systems that emulate the brain's abilities. Many of the early workers in this field of neural networks came from cybernetics; others came from neuroscience, physics, electrical engineering, mathematics, psychology, even economics. In this collection of interviews, those who helped to shape the field share their childhood memories, their influences, how they became interested in neural networks, and what they see as its future.The subjects tell stories that have been told, referred to, whispered about, and imagined throughout the history of the field. Together, the interviews form a Rashomon-like web of reality. Some of the mythic people responsible for the foundations of modern brain theory and cybernetics, such as Norbert Wiener, Warren McCulloch, and Frank Rosenblatt, appear prominently in the recollections. The interviewees agree about some things and disagree about more. Together, they tell the story of how science is actually done, including the false starts, and the Darwinian struggle for jobs, resources, and reputation. Although some of the interviews contain technical material, there is no actual mathematics in the book.ContributorsJames A. Anderson, Michael Arbib, Gail Carpenter, Leon Cooper, Jack Cowan, Walter Freeman, Stephen Grossberg, Robert Hecht-Neilsen, Geoffrey Hinton, Teuvo Kohonen, Bart Kosko, Jerome Lettvin, Carver Mead, David Rumelhart, Terry Sejnowski, Paul Werbos, Bernard WidrowFrom Library JournalThis work is not so much a collection of interviews seeking to enlighten some distinctive readership on the scientific workings of neural networks as it is a congeries of page after tedious page of the ramblings of 17 scientists who work in the vanguard of the neural field. In addition to neural networks, the work includes neurocomputing, fuzzy logic, and artificial intelligence. Anderson (linguistics, Brown) and journalist Rosenfield allow their subjects to range freely, and they discuss themselves, the neural network field (much of their offering here is anecdotal and even gossipy), and whatever happens to pop into their heads. Jerome Lettvin, professor emeritus at MIT, roams for ten pages on the question "What did your parents do?" Fuzzy logician Bart Kosko waxes nostalgic about how brilliant he was as a youth, thoughtfully into drugs and music until "a very bad acid trip, a paranoid trip, [after which] I got completely out of it and was turned off by the whole culture, including rock music." At least the glossary is good. Half-heartedly recommended for large technical collections.?Robert Ballou, AtlantaCopyright 1998 Reed Business Information, Inc.About the AuthorJames A. Anderson is Professor in the Department of Cognitive and Linguistic Sciences at Brown University.Edward Rosenfeld is editor and publisher of the newsletter Intelligence.