Recognition ability of the fully connected Hopfield neural network under a persistent stimulus field

We investigate the pattern recognition ability of the fully connected Hopfield model of a neural network under the influence of a persistent stimulus field. The model considers a biased training with a stronger contribution to the synaptic connections coming from a particular stimulated pattern. Within a mean-field approach, we computed the recognition order parameter and the full phase diagram as a function of the stimulus field strength h, the network charge α and a thermal-like noise T. The stimulus field improves the network capacity in recognizing the stimulated pattern while weakening the first-order character of the transition to the non-recognition phase. We further present simulation results for the zero temperature case. A finite-size scaling analysis provides estimates of the transition point which are very close to the mean-field prediction.

[1]  Nong Ye,et al.  Onset of traffic congestion in complex networks. , 2005, Physical review. E, Statistical, nonlinear, and soft matter physics.

[2]  Daniel J. Amit,et al.  Modeling brain function: the world of attractor neural networks, 1st Edition , 1989 .

[3]  P. Peretto,et al.  On learning rules and memory storage abilities of asymmetrical neural networks , 1988 .

[4]  Jean-Pierre Eckmann,et al.  The physics of living neural networks , 2007, 1007.5465.

[5]  V. Latora,et al.  Complex networks: Structure and dynamics , 2006 .

[6]  Tao Zhou,et al.  Immunization of susceptible–infected model on scale-free networks , 2006, physics/0610138.

[7]  J. Fontanari,et al.  Enhancing the learning of a finite number of patterns in neural networks , 1988 .

[8]  H. Horner,et al.  Transients and basins of attraction in neutral network models , 1989 .

[9]  S. Edwards,et al.  Theory of spin glasses , 1975 .

[10]  Ziyou Gao,et al.  Optimal traffic networks topology: A complex networks perspective , 2008 .

[11]  Francisco A. Tamarit,et al.  Diluted neural network with refractory periods , 1997 .

[12]  L. da Fontoura Costa,et al.  Efficient Hopfield pattern recognition on a scale-free neural network , 2002, cond-mat/0212601.

[13]  Gong,et al.  Statistical mechanics of a Hopfield neural-network model in a transverse field. , 1993, Physical review. E, Statistical physics, plasmas, fluids, and related interdisciplinary topics.

[14]  Englisch,et al.  Neural networks as perpetual information generators. , 1991, Physical review. A, Atomic, molecular, and optical physics.

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

[16]  R. Kühn,et al.  Replica symmetry breaking in attractor neural network models , 1994, cond-mat/9404036.

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

[18]  Parallel dynamics of the asymmetric extremely diluted Ashkin-Teller neural network , 1999, cond-mat/9911349.

[19]  Retrieval Properties of Neural Networks with Infinitely Many Marked Patterns , 1990 .

[20]  T J P Penna,et al.  Simulations with a large number of neurons , 1989 .

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

[22]  Yamir Moreno,et al.  Theory of Rumour Spreading in Complex Social Networks , 2007, ArXiv.

[23]  Cannas,et al.  Effects of refractory periods in the dynamics of a diluted neural network. , 1996, Physical review. E, Statistical physics, plasmas, fluids, and related interdisciplinary topics.

[24]  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.

[25]  Prabodh Shukla.  RESPONSE OF THE HOPFIELD-LITTLE MODEL IN AN APPLIED FIELD , 1997 .

[26]  G. Kohring,et al.  COMMENT: Convergence time and finite size effects in neural networks , 1990 .

[27]  Wei Li,et al.  Cluster behavior of a simple model in financial markets , 2008, Physica A: Statistical Mechanics and its Applications.

[28]  Bouten,et al.  Enlarged basin of attraction in neural networks with persistent stimuli. , 1990, Physical review. A, Atomic, molecular, and optical physics.

[29]  D. J. Wallace,et al.  Enlarging the attractor basins of neural networks with noisy external fields , 1991 .

[30]  Xiaoming Zhang,et al.  How scale-free networks and large-scale collective cooperation emerge in complex homogeneous social systems. , 2007, Physical review. E, Statistical, nonlinear, and soft matter physics.

[31]  R. Palmer,et al.  Introduction to the theory of neural computation , 1994, The advanced book program.

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

[33]  R. Dickman,et al.  Dynamic stability in random and scale-free B-lymphocyte networks. , 2007, Physical review. E, Statistical, nonlinear, and soft matter physics.

[34]  C. D. Silva.  Categorization ability in a biologically motivated neural network , 2001 .

[35]  Carla Perrone-Capano,et al.  Activity-dependent neural network model on scale-free networks. , 2007, Physical review. E, Statistical, nonlinear, and soft matter physics.

[36]  TamGas Geszti,et al.  Physical Models of Neural Networks , 1990 .

[37]  Daniel J. Amit,et al.  Neural potentials as stimuli for attractor neural networks , 1990 .

[38]  Damage Propagation in a Diluted Asymmetric Neural Network , 1998 .

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

[40]  F. Attneave,et al.  The Organization of Behavior: A Neuropsychological Theory , 1949 .

[41]  M P Singh.  Hopfield model with self-coupling. , 2001, Physical review. E, Statistical, nonlinear, and soft matter physics.

[42]  R. Kühn,et al.  Averaging and finite-size analysis for disorder: The Hopfield model , 1996 .

[43]  Markus Brede,et al.  Patterns in randomly evolving networks: idiotypic networks. , 2003, Physical review. E, Statistical, nonlinear, and soft matter physics.

[44]  F. Lillo,et al.  Topology of correlation-based minimal spanning trees in real and model markets. , 2002, Physical review. E, Statistical, nonlinear, and soft matter physics.

[45]  Hans J Herrmann,et al.  Spreading gossip in social networks. , 2007, Physical review. E, Statistical, nonlinear, and soft matter physics.

[46]  Reuven Cohen,et al.  Efficient immunization strategies for computer networks and populations. , 2002, Physical review letters.

[47]  M. Idiart,et al.  Retrieval-time properties of the Little-Hopfield model and their physiological relevance. , 2005, Physical review. E, Statistical, nonlinear, and soft matter physics.

[48]  G. J. Rodgers,et al.  Traffic on complex networks: Towards understanding global statistical properties from microscopic density fluctuations. , 2004, Physical review. E, Statistical, nonlinear, and soft matter physics.

[49]  M E J Newman,et al.  Finding and evaluating community structure in networks. , 2003, Physical review. E, Statistical, nonlinear, and soft matter physics.