Learning systems for automatic control

Recent developments in learning systems for automatic control are discussed from the point of view of pattern recognition. The following mathematical areas are given special attention: 1) decision theory, which produces control policies from gradually adjusted estimates of pattern probabilities, 2) trainable threshold logic, which produces control policies from networks of adjustable threshold devices, 3) stochastic approximation, which produces asymptotically optimum controllers, and 4) Markov chain theory, which provides an approach to modelling the dynamics of learning controllers. Projected applications in the following areas are discussed: process control, automated design of controllers, reliability control, numerical computation, and communication systems. A selected bibliography is included.

[1]  R. O. Duda,et al.  TRAINING A THRESHOLD LOGIC UNIT WITH IMPERFECTLY CLASSIFIED PATTERNS , 1944 .

[2]  William Feller,et al.  An Introduction to Probability Theory and Its Applications , 1951 .

[3]  J. Kiefer,et al.  Stochastic Estimation of the Maximum of a Regression Function , 1952 .

[4]  Claude E. Shannon,et al.  Computers and Automata , 1953, Proceedings of the IRE.

[5]  J. Blum.  Multidimensional Stochastic Approximation Methods , 1954 .

[6]  A. Dvoretzky.  On Stochastic Approximation , 1956 .

[7]  Richard C. Atkinson,et al.  A markov model for discrimination learning , 1958 .

[8]  Philip M. Lewis,et al.  Approximating Probability Distributions to Reduce Storage Requirements , 1959, Information and Control.

[9]  David T. Brown,et al.  A Note on Approximations to Discrete Probability Distributions , 1959, Inf. Control..

[10]  A. M. Uttley,et al.  The Design of Conditional Probability Computers , 1959, Inf. Control..

[11]  M. Margolis,et al.  A parameter tracking servo for adaptive control systems , 1959 .

[12]  E. H. Barnett.  Introduction to Evolutionary Operation , 1960 .

[13]  M. E. Maron,et al.  On Relevance, Probabilistic Indexing and Information Retrieval , 1960, JACM.

[14]  G. Turin,et al.  An introduction to matched filters , 1960, IRE Trans. Inf. Theory.

[15]  E. Gilbert.  Capacity of a burst-noise channel , 1960 .

[16]  Ivan Flores,et al.  Optimization of Reference Signals for Character Recognition Systems , 1960, IRE Trans. Electron. Comput..

[17]  J. Bertram.  Control by stochastic adjustment , 1960, Transactions of the American Institute of Electrical Engineers, Part II: Applications and Industry.

[18]  Philip M. Lewis.  A Note on Realization of Decision Networks Using Summation Elements , 1961, Inf. Control..

[19]  R. F. Daly.  ADAPTIVE BINARY DETECTORS , 1961 .

[20]  M. L. Tsetlin.  On the Behavior of Finite Automata in Random Media , 1961 .

[21]  Robert Hooke,et al.  `` Direct Search'' Solution of Numerical and Statistical Problems , 1961, JACM.

[22]  Kenneth H. Reid,et al.  Design Studies of Conditional Probability Computers , 1962 .

[23]  Norman M. Abramson,et al.  Learning to recognize patterns in a random environment , 1962, IRE Trans. Inf. Theory.

[24]  David J. Braverman,et al.  Learning Filters for Optimum Pattern Recognition , 1962, IRE Trans. Inf. Theory.

[25]  Jack Lee. Rosenfeld.  Adaptive decision processes , 1962 .

[26]  R. O. Winder,et al.  THRESHOLD LOGIC IN ARTIFICIAL INTELLIGENCE , 1962 .

[27]  George S. Sebestyen,et al.  Pattern recognition by an adaptive process of sample set construction , 1962, IRE Trans. Inf. Theory.

[28]  Melvin J. Hinich,et al.  A Model for a Self-Adapting Filter , 1962, Inf. Control..

[29]  Philip M. Lewis,et al.  The characteristic selection problem in recognition systems , 1962, IRE Trans. Inf. Theory.

[30]  H. Kushner.  A versatile stochastic model of a function of unknown and time varying form , 1962 .

[31]  J. E. Gibson,et al.  Adaptive Learning Systems , 2017 .

[32]  H. D. Block.  The perceptron: a model for brain functioning. I , 1962 .

[33]  J. Hsu,et al.  Decision-making in adaptive control systems , 1962 .

[34]  Paul W. Cooper,et al.  The Hypersphere in Pattern Recognition , 1962, Inf. Control..

[35]  M. Kanefsky,et al.  On adaptive detectors for two-input systems , 1963 .

[36]  L. A. Zadeh,et al.  On the definition of adaptivity , 1963 .

[37]  Philip Kaszerman,et al.  A Geometric Test-Synthesis Procedure for a Threshold Device , 1963, Inf. Control..

[38]  Karl Steinbuch,et al.  Learning Matrices and Their Applications , 1963, IEEE Trans. Electron. Comput..

[39]  Y. Ho.  On the stochastic approximation method and optimal filtering theory , 1963 .

[40]  P. Eykhoff,et al.  Some fundamental aspects of process-parameter estimation , 1963 .

[41]  J. Benes.  On systems with automatic control of configuration , 1963 .

[42]  J A Swets,et al.  Information Retrieval Systems. , 1963, Science.

[43]  H. J. Kushner,et al.  Adaptive techniques for the optimization of binary detection systems , 1963 .

[44]  Harold J. Kushner,et al.  Hill Climbing Methods for the Optimization of Multiparameter Noise Disturbed Systems , 1963 .

[45]  John H. Andreae,et al.  STELLA: A scheme for a learning machine , 1963 .

[46]  Harold J. Kushner,et al.  A Simple Iterative Procedure for the Identification of the Unknown Parameters of a Linear Time Varying Discrete System , 1963 .

[47]  C. T. Leondes,et al.  A Model Referenced Parameter Tracking Technique for Adaptive Control Systems I-The Principle of Adaptation , 1963, IEEE Transactions on Applications and Industry.

[48]  Albert B Novikoff,et al.  ON CONVERGENCE PROOFS FOR PERCEPTRONS , 1963 .

[49]  Minoru Sakaguchi.  Information Pattern, Learning Structure, and Optimal Decision Rule , 1963, Inf. Control..

[50]  S. Paszkowski.  Adaptive control for a system with a finite number of states , 1963 .

[51]  K. Narendra,et al.  An adaptive procedure for controlling undefined linear processes , 1964 .

[52]  David B. Cooper,et al.  Adaptive Pattern Recognition and Signal Detection Using Stochastic Approximation , 1964, IEEE Trans. Electron. Comput..

[53]  J. Sklansky.  TWO-MODE THRESHOLD LEARNING. , 1964 .

[54]  K. S. Fu,et al.  A computer-simulated on-line experiment in learning control systems , 1964, AFIPS '64 (Spring).

[55]  H. A. Barker,et al.  A Soloution of the Identification Problem , 1964, IEEE Transactions on Applications and Industry.

[56]  Alan G. Konheim,et al.  Linear and Nonlinear Methods in Pattern Classification , 1964, IBM J. Res. Dev..

[57]  D. A. Norman.  Stochastic Learning and a Quantal Model of Signal Detection , 1964, IEEE Transactions on Applications and Industry.

[58]  Harold J. Kushner,et al.  A New Method of Locating the Maximum Point of an Arbitrary Multipeak Curve in the Presence of Noise , 1964 .

[59]  P. Dorato,et al.  Optimallty, insensitivity, and game theory , 1964 .

[60]  Rob J. Roy,et al.  A hybrid computer for adaptive nonlinear process identification , 1964, AFIPS '64 (Fall, part I).

[61]  M. Levin.  Estimation of a system pulse transfer function in the presence of noise , 1964 .

[62]  K. Kumar,et al.  On the identification of control systems by the quasi-linearization method , 1964 .

[63]  Rob J. Roy,et al.  Nonlinear process identification using statistical pattern matrices , 1964 .

[64]  L. N. Kanal,et al.  Recognition system design by statistical analysis , 1964 .

[65]  M. Aizerman,et al.  Theoretical Foundations of the Potential Function Method in Pattern Recognition Learning , 1964 .

[66]  N. Puri,et al.  Transfer Function Tracking of a Linear Time-Varying System By Means of Auxiliary Simple Lag Networks , 1964, IEEE Transactions on Applications and Industry.

[67]  David B. Cooper,et al.  Nonsupervised Adaptive Signal Detection and Pattern Recognition , 1964, Inf. Control..

[68]  K. Fu,et al.  A heuristic approach to reinforcement learning control systems , 1965 .

[69]  King-Sun Fu,et al.  A learning control system using stochastic approximation for hill-climbing , 1965 .

[70]  Laveen N. Kanal,et al.  Classification of binary random patterns , 1965, IEEE Trans. Inf. Theory.

[71]  C. Hugh Mays.  The Relationship of Algorithms Used with Adjustable Threshold Elements to Differential Equations , 1965, IEEE Trans. Electron. Comput..

[72]  Jack Sklansky.  Threshold training of two-mode signal detection , 1965, IEEE Trans. Inf. Theory.

[73]  Yu-Chi Ho,et al.  Identification of Linear Dynamic Systems , 1964, Inf. Control..