Summary
Self-improving control systems may belong to either of two categories, according to whether or not they embody an explicit model of the part of their environment with which they interact. The two forms of operation are discussed and compared, and it is shown that the two may be mathematically equivalent. The treatment also gives theoretical justification for a particular mode of operation for nonmodel-forming controllers.
Similar content being viewed by others
References
Kalman, R. E.: Design of self-optimizing control system. Trans. A.S.M.E., Feb. 1958, p. 468.
Craik, K. J. W.: The nature of explanation. Cambridge: Cambridge University Press 1943 and 1952.
Selfridge, O. G.: Pattern recognition and learning. Information theory: ed. E. C. Cheery, p. 345. London: Butterworth & Co. 1956.
Andrew, A. M.: Learning machines. Mechanisation of thought processes, p. 473. London: H.M.S.O. 1959.
Donaldson, P. E. K.: Error decorrelation: a technique for matching a class of functions. Proc. 3rd Int. Conf. on Medical Electronics, p. 173, London 1960.
Andrew, A. M.: An experimental comparison of some algorithms for self-organising systems. I.R.E. Trans. Inform. Theory IT-8, p. 163, 1962.
Gabor, D., W. P. L. Wilby, and R. Woodcock: A universal non-linear filter, predictor and simulator which optimises itself by a learning process. Proc. Inst. Electr. Engrs (Lond.), pt. B, 108, 422 (1961).
Lubbock, J. K.: A self-optimising non-linear filter. Proc. Inst. Electr. Engrs (Lond.), pt. B, 108, 439 (1961).
Nilsson, N. J.: Learning machines. Maidenhead/Berks.: McGraw-Hill Book Co. 1965.
Weatherburn, C. E.: A first course in mathematical statistics, p. 247. Cambridge: Cambridge University Press 1952.
Andrew, A. M.: Self-improvement using a disturbed measure of goal-achievement. IFAC Congress, London 1966.
Nightingale, J. M.: Digital adaptive control system employing a normalised performance index. Proc. Inst. Electr. Engrs (Lond.), 111, 165 (1964).
Gabor, D.: Communication theory and cybernetics. Trans. I.R.E., CT-1, No 4, 19 (1954).
Andrew, A. M.: Automatic adjustment in a continuous environment. Internal report, Biological Computer Lab., Univ. of Illinois 1965.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Andrew, A.M. To model or not to model. Kybernetik 3, 272–275 (1967). https://doi.org/10.1007/BF00271509
Received:
Issue Date:
DOI: https://doi.org/10.1007/BF00271509