Dynamics of Spin Glasses and Related Models of Neural Networks

Retrieval of information from a neural network, used as auto-associative memory, is viewed as a dynamic process built from a linear mapping and a local nonlinear rectification. Two types of dynamics are compared: Glauber or Monte Carlo dynamics, the process usually adopted for spin glasses, and dynamics based on differential equations for the generating potentials of neurons. For the second type retrieval takes place via successive refinement and this yields an improved performance in the reconstruction of patterns.

[1]  D. O. Hebb,et al.  The organization of behavior , 1988 .

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

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

[4]  K. Binder,et al.  Spin glasses: Experimental facts, theoretical concepts, and open questions , 1986 .

[5]  R. Glauber.  Time‐Dependent Statistics of the Ising Model , 1963 .

[6]  Stanislas Dehaene,et al.  Networks of Formal Neurons and Memory Palimpsests , 1986 .

[7]  Néstor Parga,et al.  The ultrametric organization of memories in a neural network , 1986 .

[8]  G Palm,et al.  Brain Theory , 1986, Springer Berlin Heidelberg.

[9]  J. Hopfield,et al.  Computing with neural circuits: a model. , 1986, Science.

[10]  S Dehaene,et al.  Spin glass model of learning by selection. , 1986, Proceedings of the National Academy of Sciences of the United States of America.

[11]  P E Roland,et al.  Localization of cortical areas activated by thinking. , 1985, Journal of neurophysiology.

[12]  J J Hopfield,et al.  Neurons with graded response have collective computational properties like those of two-state neurons. , 1984, Proceedings of the National Academy of Sciences of the United States of America.

[13]  Opper,et al.  Learning of correlated patterns in spin-glass networks by local learning rules. , 1987, Physical review letters.

[14]  G. Parisi.  A memory which forgets , 1986 .

[15]  G. Toulouse,et al.  Ultrametricity for physicists , 1986 .