About this Item
AI and Michie's MENACE
Donald Michie "Trial and Error" [Can Machines Think?] in Penguin Science Survey 2, 1961. London, Penguin Books, 1961, first edition. The Michie is on pp 129-145 in the volume of 251pp (with 6 plates printed on glossy paper). Original plasticized wrappers. If you put the book flat on the table the cover will curl up by about 1.5" which is due, I think, because of age and the material (see pic). That said this would have been a near-Fine copy.
Donald Michie, (1923-2007) was a British researcher and pioneer in artificial intelligence and game theory. During World War II, Michie worked with Alan Turing at Bletchley Park, with Jack Good and Shaun Wylie et al. in the section Newmanry headed by Max Newman, contributing to crack the German Lorenz cipher. In 1947-48, along with Wylie, Michie designed Machiavelli, a rival of Turing's Turochamp program. Michie was head of the University of Edinburgh's Department of Machine Intelligence from 1965 until 1985, when he left to found the Turing Institute in Glasgow."
"Michie began his first experiments in machine learning in 1960. His tic-tac toe machine MENACE (Machine Educable Noughts And Crosses Engine) demonstrated the basic principle of a self-reinforcing learning mechanism. MENACE employed Michie's conceptually simple general-purpose learning algorithm BOXES which could also discover robust control strategies for the pole balancing problem, but was soon employed industrially to evolve strategies for automatic control, such as controlling a steel mill."--from the chessprogramming wiki site 714.3
"The Matchbox Educable Noughts and Crosses Engine (sometimes called the Machine Educable Noughts and Crosses Engine or MENACE) was a mechanical computer made from 304 matchboxes designed and built by artificial intelligence researcher Donald Michie and his colleague Roger Chambers, in 1961. It was designed to play human opponents in games of noughts and crosses (tic-tac-toe) by returning a move for any given state of play and to refine its strategy through reinforcement learning. This was one of the first types of artificial intelligence."
"Michie and Chambers did not have immediate access to a computer; they worked around this by building the engine out of matchboxes. The matchboxes they used each represented a single possible layout of a noughts and crosses grid. When the computer first played, it would randomly choose moves based on the current layout. As it played more games, through a reinforcement loop, it disqualified strategies that led to losing games, and supplemented strategies that led to winning games. Michie held a tournament against MENACE in 1961, wherein he experimented with different openings."--wikipedia.
Seller Inventory # ABE-1772937952287
Contact seller
Report this item
