Learning systems: theory and application

A survey of the state of the art in learning systems (automata and neural networks) which are of increasing importance in both theory and practice is presented. Learning systems are a response to engineering design problems arising from nonlinearities and uncertainty. Definitions and properties of learning systems are detailed. An analysis of the reinforcement schemes which are the heart of learning systems is given. Some results related to the asymptotic properties of the learning automata are presented as well as the learning systems models, and at the same time the controller (optimiser) and the controlled process (criterion to be optimised). Two learning schemes for neural networks synthesis are presented. Several applications of learning systems are also described. >

[1]  C. Dorea Stopping rules for a random optimization method , 1990 .

[2]  Bernard Widrow,et al.  30 years of adaptive neural networks: perceptron, Madaline, and backpropagation , 1990, Proc. IEEE.

[3]  Mandayam A. L. Thathachar,et al.  Learning Optimal Discriminant Functions through a Cooperative Game of Automata , 1987, IEEE Transactions on Systems, Man, and Cybernetics.

[4]  I︠a︡. Z. T︠S︡ypkin,et al.  Foundations of the theory of learning systems , 1973 .

[5]  Y. M. El-Fattah,et al.  Learning Systems: Decision, Simulation, and Control , 1978 .

[6]  E. Zafiriou,et al.  Use of neural networks for sensor failure detection in a control system , 1990, IEEE Control Systems Magazine.

[7]  Richard Lippmann,et al.  Review of Neural Networks for Speech Recognition , 1989, Neural Computation.

[8]  Geoffrey E. Hinton,et al.  Phoneme recognition using time-delay neural networks , 1989, IEEE Trans. Acoust. Speech Signal Process..

[9]  Kumpati S. Narendra,et al.  Learning Automata - A Survey , 1974, IEEE Trans. Syst. Man Cybern..

[10]  J. Sklansky,et al.  Learning systems for automatic control , 1966 .

[11]  Robert M. Glorioso Engineering Intelligent Systems , 1980 .

[12]  B. Chandrasekaran,et al.  On Expediency and Convergence in Variable-Structure Automata , 1968, IEEE Trans. Syst. Sci. Cybern..

[13]  N.V. Bhat,et al.  Modeling chemical process systems via neural computation , 1990, IEEE Control Systems Magazine.

[14]  S. Lakshmivarahan,et al.  Learning Algorithms Theory and Applications , 1981 .

[15]  Kumpati S. Narendra,et al.  Games of Stochastic Automata , 1974, IEEE Trans. Syst. Man Cybern..

[16]  S.S. Rangwala,et al.  Learning and optimization of machining operations using computing abilities of neural networks , 1989, IEEE Trans. Syst. Man Cybern..

[17]  K. R. Ramakrishnan,et al.  A cooperative game of a pair of learning automata , 1984, Autom..

[18]  S. Zamir On the Notion of Value for Games with Infinitely Many Stages , 1973 .

[19]  Eduardo D. Sontag,et al.  Backpropagation Can Give Rise to Spurious Local Minima Even for Networks without Hidden Layers , 1989, Complex Syst..

[20]  K S Narendra,et al.  IDENTIFICATION AND CONTROL OF DYNAMIC SYSTEMS USING NEURAL NETWORKS , 1990 .

[21]  Frederick Mosteller,et al.  Stochastic Models for Learning , 1956 .

[22]  Philip M. Morse,et al.  Introduction to the Theory of Games , 1952 .

[23]  Norio Baba,et al.  On the Learning Behavior of Stochastic Automata Under a Nonstationary Random Environment , 1975, IEEE Transactions on Systems, Man, and Cybernetics.

[24]  Norio Baba,et al.  Two ε-Optimal Nonlinear Reinforcement Schemes for Stochastic Automata , 1974, IEEE Trans. Syst. Man Cybern..

[25]  Howard Raiffa,et al.  Games And Decisions , 1958 .

[26]  M. Thathachar,et al.  Bounds on the Convergence Probabilities of Learning Automata , 1976 .

[27]  Kaddour Najim,et al.  Modelling and learning control of rotary phosphate dryer , 1989 .

[28]  Teuvo Kohonen,et al.  The self-organizing map , 1990 .

[29]  H. Kushner Stochastic approximation algorithms for the local optimization of functions with nonunique stationary points , 1972 .

[30]  R. Duncan Luce,et al.  Individual Choice Behavior , 1959 .

[31]  Kumpati S. Narendra,et al.  Adaptation and learning in automatic systems , 1974 .

[32]  Hendrik Van Brussel,et al.  A self-learning automaton with variable resolution for high precision assembly by industrial robots , 1982 .

[33]  Norio Baba The absolutely expedient nonlinear reinforcement schemes under the unknown multiteacher environment , 1983, IEEE Transactions on Systems, Man, and Cybernetics.

[34]  B. John Oommen,et al.  Learning automata processing ergodicity of the mean: The two-action case , 1983, IEEE Transactions on Systems, Man, and Cybernetics.

[35]  K. Narendra,et al.  Learning Algorithms for Two-Person Zero-Sum Stochastic Games with Incomplete Information: A Unified Approach , 1982 .

[36]  Peter T. Cummings,et al.  Process optimization via simulated annealing: Application to network design , 1989 .

[37]  B. Chandrasekaran,et al.  Stochastic Automata Games , 1969, IEEE Trans. Syst. Sci. Cybern..

[38]  Robert B. Allen,et al.  Learning of stable states in stochastic asymmetric networks , 1990, IEEE Trans. Neural Networks.

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

[40]  F. Girosi,et al.  Networks for approximation and learning , 1990, Proc. IEEE.

[41]  James A. Anderson,et al.  Neurocomputing: Foundations of Research , 1988 .

[42]  R. Kashyap,et al.  Optimization of stochastic finite state systems , 1966 .

[43]  Leonardo Reyneri,et al.  Modified backpropagation algorithm for fast learning in neural networks , 1990 .

[44]  L. G. Mason,et al.  Learning Automata Models for Adaptive Flow Control in Packet-Switching Networks , 1986 .

[45]  Rein Luus,et al.  Reliability of optimization procedures for obtaining global optimum , 1978 .

[46]  M. Thathachar,et al.  A Hierarchical System of Learning Automata , 1981, IEEE Transactions on Systems, Man, and Cybernetics.

[47]  B. Ydstie Forecasting and control using adaptive connectionist networks , 1990 .

[48]  W. Thomas Miller,et al.  Real-time application of neural networks for sensor-based control of robots with vision , 1989, IEEE Trans. Syst. Man Cybern..

[49]  K. Najim,et al.  Optimization technique based on learning automata , 1990 .

[50]  P. Mars,et al.  Application of Learning Automata to Image Data Compression , 1986 .

[51]  K. Najim Multivariable control of a liquid-liquid extraction column using a probabilistic automaton , 1988 .

[52]  BART KOSKO,et al.  Bidirectional associative memories , 1988, IEEE Trans. Syst. Man Cybern..

[53]  J. G. Taylor,et al.  Noisy neural net states and their time evolution , 1990 .

[54]  Kumpati S. Narendra,et al.  Recent Developments in Learning Automata , 1986 .

[55]  Josiah C. Hoskins,et al.  Artificial neural network models for knowledge representation in chemical engineering , 1990 .

[56]  Kaddour Najim,et al.  Multivariable learning control of an extractor , 1988 .

[57]  M. V. Le Lann,et al.  CONTROL OF A PULSED LIQUID-LIQUID EXTRACTION COLUMN BASED ON A MULTILEVEL SYSTEM OF AUTOMATA , 1988 .

[58]  King-Sun Fu,et al.  An algorithm for learning without external supervision and its application to learning control systems , 1966 .

[59]  Kumpati S. Narendra,et al.  Learning automata - an introduction , 1989 .

[60]  H.E. Rauch,et al.  Neural networks for routing communication traffic , 1988, IEEE Control Systems Magazine.

[61]  B. R. Harita,et al.  Learning automata with changing number of actions , 1987, IEEE Transactions on Systems, Man, and Cybernetics.

[62]  Shun-ichi Amari,et al.  Mathematical foundations of neurocomputing , 1990, Proc. IEEE.

[63]  David J. Burr,et al.  Experiments on neural net recognition of spoken and written text , 1988, IEEE Trans. Acoust. Speech Signal Process..