MTU Library Catalogue

Syndetics cover image
Image from Syndetics

Perceptrons : an introduction to computational geometry / Marvin Minsky and Seymour Papert.

By: Minsky, Marvin, 1927-2016.
Contributor(s): Papert, Seymour.
Material type: materialTypeLabelBookPublisher: Cambridge, Mass. : MIT Press, 1969 1988Edition: Expanded ed.Description: xv, 292 p. : ill. ; 23 cm. + pbk.ISBN: 0262631113 .Subject(s): Perceptrons | Geometry -- Data processing | Parallel processing (Electronic computers) | Machine learningDDC classification: 006.3
Contents:
Introduction -- I: Algebraic theory of linear parallel predicates -- Theory of linear boolean inequalities -- Group invariance of boolean inequalities -- Parity and one-in-a-box predicates -- The " And/Or" theorem -- II: Geometric theory of linear inequalities -- connected: A geometric property with unbounded order -- Geometric patterns of small order: Spectra and context -- Stratification and normalization -- The diameter-limited perception -- Geometric predicates and serial algorithms -- III: Learning theory -- Magnitude of the coefficients -- Learning -- Linear separation and learning -- Perceptions and pattern recognition.

Enhanced descriptions from Syndetics:

Perceptrons -- the first systematic study of parallelism in computation -- has remained a classical work on threshold automata networks for nearly two decades. It marked a historical turn in artificial intelligence, and it is required reading for anyone who wants to understand the connectionist counterrevolution that is going on today.

Artificial-intelligence research, which for a time concentrated on the programming of Von Neumann computers, is swinging back to the idea that intelligence might emerge from the activity of networks of neuronlike entities. Minsky and Papert's book was the first example of a mathematical analysis carried far enough to show the exact limitations of a class of computing machines that could seriously be considered as models of the brain. Now the new developments in mathematical tools, the recent interest of physicists in the theory of disordered matter, the new insights into and psychological models of how the brain works, and the evolution of fast computers that can simulate networks of automata have given Perceptrons new importance.

Witnessing the swing of the intellectual pendulum, Minsky and Papert have added a new chapter in which they discuss the current state of parallel computers, review developments since the appearance of the 1972 edition, and identify new research directions related to connectionism. They note a central theoretical challenge facing connectionism: the challenge to reach a deeper understanding of how "objects" or "agents" with individuality can emerge in a network. Progress in this area would link connectionism with what the authors have called "society theories of mind."

Bibliography: pages 281-287) and index.

Introduction -- I: Algebraic theory of linear parallel predicates -- Theory of linear boolean inequalities -- Group invariance of boolean inequalities -- Parity and one-in-a-box predicates -- The " And/Or" theorem -- II: Geometric theory of linear inequalities -- connected: A geometric property with unbounded order -- Geometric patterns of small order: Spectra and context -- Stratification and normalization -- The diameter-limited perception -- Geometric predicates and serial algorithms -- III: Learning theory -- Magnitude of the coefficients -- Learning -- Linear separation and learning -- Perceptions and pattern recognition.

Author notes provided by Syndetics

Seymour Aubrey Papert was born in Pretoria, South Africa on February 29, 1928. He received doctorates from the University of the Witwatersrand in South Africa and the University of Cambridge in England. After his doctoral work, he spent four years at the University of Geneva exploring both mathematics and children's learning as a researcher for Jean Piaget. In 1964, he joined the Massachusetts Institute of Technology faculty and immediately delved into artificial intelligence research with Marvin Minsky. He was a co-director of the renowned Artificial Intelligence Laboratory at the Massachusetts Institute of Technology. Papert and Minsky published Perceptrons: An Introduction to Computational Geometry in 1969.

Papert foresaw children using computers as instruments for learning and enhancing creativity well before the advent of the personal computer. In the late 1960's, he created a computer programming language, called Logo, to teach children how to use computers. He wrote several other books including Mindstorms: Children, Computers and Powerful Ideas and Constructionism written with Idit Harel. Papert retired from the faculty at M.I.T. in 1996, but continued to work there as a lecturer and consultant to doctoral students. He died from complications of a series of kidney and bladder infections on July 31, 2016 at the age of 88.

(Bowker Author Biography)