An introduction to natural computation
著者
書誌事項
An introduction to natural computation
（Complex adaptive systems）
MIT Press, c1997
- : hardcover
大学図書館所蔵 件 / 全43件
-
該当する所蔵館はありません
- すべての絞り込み条件を解除する
注記
Includes bibliographical references and index
"A Bradford Book"
内容説明・目次
内容説明
"This is a wonderful book that brings together in one place the modern view of computation as found in nature. It is well written and has something for everyone from the undergraduate to the advanced researcher."
-- Terrence J. Sejnowski, Howard Hughes Medical Institute at The Salk Institute for Biological Studies, La Jolla, California It is now clear that the brain is unlikely to be understood without recourse to computational theories. The theme of An "Introduction to Natural Computation" is that ideas from diverse areas such as neuroscience, information theory, and optimization theory have recently been extended in ways that make them useful for describing the brain's programs. This book provides a comprehensive introduction to the computational material that forms the underpinnings of the currently evolving set of brain models. It stresses the broad spectrum of learning models--ranging from neural network learning through reinforcement learning to genetic learning--and situates the various models in their appropriate neural context. To write about models of the brain before the brain is fully understood is a delicate matter. Very detailed models of the neural circuitry risk losing track of the task the brain is trying to solve. At the other extreme, models that represent cognitive constructs can be so abstract that they lose all relationship to neurobiology. An "Introduction to Natural Computation" takes the middle ground and stresses the computational task while staying near the neurobiology. The material is accessible to advanced undergraduates as well as beginning graduate students.
CONTENTS: 1. Introduction
Part I "Core Concepts" 2. Fitness 3. Programs 4. Data 5. Dynamics 6. Optimization
Part II "Memories" 7. Content Addressible Memories 8. Supervised Learning 9. Unsupervised Learning
Part III "Programs" 10. Markov Models 11. Reinforcement Learning
Part IV "Systems" 12. Genetic Algorithms
目次
- Natural computation: introduction
- the brain
- computational theory
- elements of natural computation
- overview
- the grand challenge
- notes
- exercises. Part 1 Core concepts: fitness - introduction, Baye's rule, probability distributions, information theory, appendix: laws of probability, notes, exercises
- programs - introduction, heuristic search, two-person games, biological state spaces, notes, exercises
- data - data compression, coordinate systems, Eigenvalues and Eigenvectors, random vectors, high-dimensional spaces, clustering, appendix: linear algebra review, notes, exercises
- dynamics - overview, linear systems, nonlinear systems, appendix: taylor series, notes, exercises
- optimization - introduction minimization algorithms, the method of Lagrange multipliers, optimal control . Part 2 Memories: content-addressable memory - introduction, Hopfield memories, Kanerva memories, radial basis functions, Kalman filtering, notes, exercises
- supervised learning - introduction, perceptions, continuous activation functions, recurrent networks, minimum description length, the activation function, notes, exercises
- unsupervised learning - introduction, principal components, competitive learning, topological constraints, supervised competitive learning, multimodal data, independent components, notes, exercises. Part 3 Programs: Markov models - hidden Markov models - notes, exercises
- reinforcement learning - introduction, Markov decision process, the Core ideas - policy improvement, Q-learning, temporal-difference learning, learning with a teacher, partially observable MDPs, summary, notes, exercises. Part 4 Systems: genetic algorithms - introduction, schemata, determining fitness
- genetic programming - introduction, genetic operators for programs, genetic programming, analysis, modules, summary
- summary - learning to react - memories, learning during a lifetime - programs, learning across generations - systems, the grand challenge revisited, note.
「Nielsen BookData」 より