Abstract
The development of the physics of living systems is caused by the necessity of considering the specific features of their adaptive search behavior. This is one of the main properties of living systems distinguishing adaptable living systems from mechanisms and cybernetic robots. An efficient method for studying the adaptive properties of living systems is the construction and investigation of neural network models of human and animal brains ensuring highly efficient behavior under complex dynamic environmental conditions. In [1] we have already suggested the mathematical formalism for a description of self-adapting neural networks and their training that can be used to model the self-organization processes in open living systems. In the present paper, new neural network algorithms of this class are suggested. New capabilities of these algorithms inaccessible for the conventional supervisory algorithms of neural network training are examined.
Similar content being viewed by others
REFERENCES
T. F. Baskanova and Yu. P. Lankin, Izv. Vyssh. Uchebn. Zaved., Fiz., No. 6, 47-51 (2000).
E. Schrödinger, What Is Life [Russian translation]?, Mir, Moscow (1972).
G. Nicolis and I. Prigozhin, Comprehension of Complexity [Russian translation], Mir, Moscow (1990).
W. R. Ashby, Introduction to Cybernetics [Russian translation], Inostrannaya Literatura, Moscow (1959).
Yu. V. Chaikovskii, Principles of Evolutionary Diatropism [in Russian], Nauka, Moscow (1990).
Yu. P. Lankin and R. G. Khlebopros, Inzhen. Ékol., No. 2, 2-26 (2001).
H. 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 of the USSR Academy of Sciences, Krasnoyarsk (1986), 19 pp.
A. N. Gorban', Sib. Zh. Vychisl. Mat., 1, No. 1, 11-24 (1998).
F. P. Vasil'ev, Numerical Methods of Solving Extremum Problems [in Russian], Nauka, Moscow (1988).
Yu. P. Lankin, Preprint No. TO4, Institute of Biophysics of the SB RAS, Krasnoyarsk (1998), 17 pp.
Yu. P. Lankin, in: Proc. All-Russian Sci.-Tech. Conf. Neiroinformatiks-99, Part 3 [in Russian], Moscow (1999), pp. 278-284.
Yu. P. Lankin, A. N. Zemlyanskii, S. V. Plotnikov, et al., Inzhen. Ékol., No. 3, 3-18 (2000).
Yu. P. Lankin and S. A. Putilov, in: Proc. 3rd All-Russian Scientific-Technical Conf. Neiroinformatiks-2001, Part 2 [in Russian], Moscow (2001), pp. 102-107.
Yu. P. Lankin, Preprint No. TO3, Institute of Biophysics of the SB RAS, Krasnoyarsk (1997), 21 pp.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Baskanova, T.F., Lankin, Y.P. Training of Neural Networks with Search Behaviour. Russian Physics Journal 45, 389–393 (2002). https://doi.org/10.1023/A:1020535225240
Issue Date:
DOI: https://doi.org/10.1023/A:1020535225240