Multiconnected neural network models

A generalisation of the Hopfield model which includes interactions between p()2) Ising spins is considered. The exact storage capacity behaves as Np-1/2(p-1)! ln N when the number of nodes, N, is large. In the limit p to infinity , the thermodynamics of the model can be solved exactly without using the replica method; at zero temperature, a solution which is completely correlated with the input pattern exists for alpha < alpha c where alpha c to infinity as p to infinity and this solution has lower energy than the spin-glass solution if alpha < alpha 1=1/4 ln 2 where the number of patterns n=(2 alpha /p!)Np-1. For finite values of p, the correlation with the input pattern is not complete; for p=3 and 4, approximate values of alpha c and alpha 1 are obtained and for p to infinity the replica symmetric approximation gives alpha c approximately p/4 ln p.

[1]  S. Kirkpatrick,et al.  Solvable Model of a Spin-Glass , 1975 .

[2]  S. Kirkpatrick,et al.  Infinite-ranged models of spin-glasses , 1978 .

[3]  B. Derrida.  Random-Energy Model: Limit of a Family of Disordered Models , 1980 .

[4]  B. Derrida.  Random-energy model: An exactly solvable model of disordered systems , 1981 .

[5]  J J Hopfield,et al.  Neural networks and physical systems with emergent collective computational abilities. , 1982, Proceedings of the National Academy of Sciences of the United States of America.

[6]  M. Mézard,et al.  The simplest spin glass , 1984 .

[7]  Gérard Weisbuch,et al.  Scaling laws for the attractors of Hopfield networks , 1985 .

[8]  E. Gardner.  Spin glasses with p-spin interactions , 1985 .

[9]  Sompolinsky,et al.  Storing infinite numbers of patterns in a spin-glass model of neural networks. , 1985, Physical review letters.

[10]  Sompolinsky,et al.  Spin-glass models of neural networks. , 1985, Physical review. A, General physics.

[11]  P. Mottishaw.  First-Order Spin Glass Transitions: an Exact Solution , 1986 .

[12]  A. Crisanti,et al.  Saturation Level of the Hopfield Model for Neural Network , 1986 .

[13]  E. Gardner.  Structure of metastable states in the Hopfield model , 1986 .

[14]  James L. McClelland,et al.  Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations , 1986 .

[15]  D. J. Wallace,et al.  Dynamics and statistical mechanics of the Hopfield model , 1987 .

[16]  P. Peretto,et al.  Long term memory storage capacity of multiconnected neural networks , 2004, Biological Cybernetics.