Perceptrons: An Introduction to Computational Geometry por Marvin Minsky, Seymour A Papert, Léon Bottou

Perceptrons: An Introduction to Computational Geometry por Marvin Minsky, Seymour A Papert, Léon Bottou

Titulo del libro: Perceptrons: An Introduction to Computational Geometry

Autor: Marvin Minsky, Seymour A Papert, Léon Bottou

Número de páginas: 316 páginas

Fecha de lanzamiento: September 22, 2017

ISBN: 0262534770

Editor: Mit Press

Descargue o lea el libro de Perceptrons: An Introduction to Computational Geometry de Marvin Minsky, Seymour A Papert, Léon Bottou en formato PDF y EPUB. Aquí puedes descargar cualquier libro en formato PDF o Epub gratis. Use el botón disponible en esta página para descargar o leer libros en línea.

Descargar PDF Leer on-line

Marvin Minsky, Seymour A Papert, Léon Bottou con Perceptrons: An Introduction to Computational Geometry

Reissue of the 1988 Expanded Edition with a new foreword by Leon Bottou

In 1969, ten years after the discovery of the perceptron -- which showed that a machine could be taught to perform certain tasks using examples -- Marvin Minsky and Seymour Papert published Perceptrons, their analysis of the computational capabilities of perceptrons for specific tasks. As Leon Bottou writes in his foreword to this edition, "Their rigorous work and brilliant technique does not make the perceptron look very good." Perhaps as a result, research turned away from the perceptron. Then the pendulum swung back, and machine learning became the fastest-growing field in computer science. Minsky and Papert's insistence on its theoretical foundations is newly relevant.

Perceptrons -- the first systematic study of parallelism in computation -- marked a historic turn in artificial intelligence, returning to the idea that intelligence might emerge from the activity of networks of neuron-like entities. Minsky and Papert provided mathematical analysis that showed the limitations of a class of computing machines that could be considered as models of the brain. Minsky and Papert added a new chapter in 1987 in which they discuss the state of parallel computers, and note a central theoretical challenge: reaching 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."