The phase space of interactions in neural networks with definite symmetry

We calculate the typical fraction of the phase space of interactions which solve the problem of storing a given set of p patterns represented as N-spin configurations, as a function of the storage ratio, a = p/N, of the stability parameter, K, and of the symmetry, 7, of the interaction matrices. The calculation is performed for strongly diluted networks, where the connectivity of each spin, C, is of the order of In N. For each value of K and 17, there is a maximal value of a, above which the volume of solutions vanishes. For each value of K and a, there is a typical value of 7 at which this volume is maximal. The analytical studies are supplemented by numerical simulations on fully connected and diluted networks, using specific learning algorithms.

[1]  E. Gardner,et al.  An Exactly Solvable Asymmetric Neural Network Model , 1987 .

[2]  Opper.  Learning times of neural networks: Exact solution for a PERCEPTRON algorithm. , 1988, Physical review. A, General physics.

[3]  G. Parisi,et al.  Asymmetric neural networks and the process of learning , 1986 .

[4]  E. Gardner.  The space of interactions in neural network models , 1988 .

[5]  Thomas B. Kepler,et al.  Optimal learning in neural network memories , 1989 .

[6]  H. Gutfreund,et al.  The nature of attractors in an asymmetric spin glass with deterministic dynamics , 1988 .

[7]  Marc Mézard,et al.  The roles of stability and symmetry in the dynamics of neural networks , 1988 .

[8]  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.

[9]  E. Gardner,et al.  Maximum Storage Capacity in Neural Networks , 1987 .

[10]  Kanter,et al.  Associative recall of memory without errors. , 1987, Physical review. A, General physics.

[11]  Teuvo Kohonen,et al.  Self-Organization and Associative Memory, Third Edition , 1989, Springer Series in Information Sciences.

[12]  D. Amit,et al.  Statistical mechanics of neural networks near saturation , 1987 .

[13]  Sompolinsky,et al.  Dynamics of spin systems with randomly asymmetric bonds: Ising spins and Glauber dynamics. , 1988, Physical review. A, General physics.

[14]  I. Guyon,et al.  Information storage and retrieval in spin-glass like neural networks , 1985 .