Abstract
In the present paper, a training algorithm with nontraditional capabilities and self-adaptation is suggested for a new generation of neural networks with search behavior. The results obtained open up new opportunities for progress in the physics of living systems in the direction of modeling of purposeful search behavior at the insect level. They enable systems of adaptive control, considering changes in environmental conditions and in properties of the controllable object in the control process, to be developed. The algorithm allows both traditional supervisory training of a neural network with a priori known answers and finish learning during its functioning in accordance with preassigned criteria when knowledge of required states of neuron network outputs is lacking.
Similar content being viewed by others
References
Yu.P. Lankin, Preprint No. TO3, Institute of Biophysics of the SB RAS, Krasnoyarsk (1997), 21 pp.
Yu.P. Lankin, Preprint No. TO4, Institutes of Biophysics of the SB RAS, Krasnoyarsk (1998), 17 pp.
A.N. Gorban', Sib. Zh. Vychisl. Mat.,1, No. 1, 11–24 (1998).
D.E. Rumelhart, G.E. Hinton, and R.J. Williams, Nature,323, 533–536 (1986).
S.I. Bartsev and V.A. Okhonin, Preprint No. 59B, Institute of Biophysics of the SB RAS, Krasnoyarsk (1986), 19pp.
B. Widrow B and M.B. Hoff, IRE WESCOW Conf. Record, Part 4, 96–104 (1960).
N.S. Bakhvalov, N.P. Zhidkov, and G.M. Kobel'kov, Numerical Methods [in Russian], Nauka, Moscow (1987).
F.P. Vasil'ev, Numerical Methods of Solving Extremum Problems [in Russian], Nauka, Moscow (1988).
Yu.P. Lukashin, Adaptive Methods of Short-Term Prediction [in Russian], Statistika, Moscow (1979).
Additional information
Krasnoyarsk State University; Institute of Biophysics of the Siberian Branch of the Russian Academy of Sciences. Translated from Izvestiya Vysshikh Uchebnykh Zavedenii, Fizika, No. 6, pp. 47–51, June, 2000.
Rights and permissions
About this article
Cite this article
Baskanova, T.F., Lankin, Y.P. Self-adaptation algorithm for neural networks with search behavior. Russ Phys J 43, 483–487 (2000). https://doi.org/10.1007/BF02508628
Received:
Issue Date:
DOI: https://doi.org/10.1007/BF02508628