Desaturating coefficient for projection learning rule
A Hopfield-like neural network designed with projection learning rule is considered. The relationship between the weight values and the number of prototypes is obtained. A coefficient of self-connection reduction, termed the desaturating coefficient, is introduced and the technique which allows the network to exhibit complete error correction for learning ratios up to 75% is suggested. The paper presents experimental data and provides theoretical background explaining the results.
Unable to display preview. Download preview PDF.
- 1.Albert A. Regression and Moore-Penrose pseudoinverse, Academic New-York, 1972Google Scholar
- 2.Amit D.J., Gutfreund H. and Somplolinsky H. Spin Glass Model of Neural Networks, Phys. Rev.-A. (1985),32,p.1007–1018.Google Scholar
- 3.Gorodnichy D.O., Reznik A.M. NEUTRAM — A Transputer Based Neural Network Simulator, Proc. of Second Intern. Conf. on Software for Multiprocessors and Supercomputers Theory, Practice, Experience (SMS TPE'94), 136–142, Moscow, Russia, 1994Google Scholar
- 4.Gindi G.R., Gmitro A.F. and Parthasarathy K. Hopfield model associative memory with non-zero diagonal terms in memory matrix, Applied optics(1988), 27, 129–134Google Scholar
- 5.Marom E. Associated Memory Neural Networks with Concatenated Vectors and Nonzero Diagonal Terms, Neural Networks (1990), Vol.3, N3, 311–318Google Scholar
- 6.Personnaz I.,Guyon I.,Dreyfus G. Information storage and retrieval in spin-glass like neural networks, J.Physique Lett.(1985),46, L359Google Scholar
- 7.Personnaz I.,Guyon I.,Dreyfus G. Collective computational properties of neural networks: New learning mechanisms, Phys. Rev.-A. (1986),34,N5,p.4217–4228.Google Scholar
- 8.Yanai H. and Sawada Y. Associative memory network composed of neurons with Hysteretic Property, Neural Networks (1990), Vol.3, N2, 223–228.Google Scholar