Retrieval Dynamics in Oscillator Neural Networks

We present an analytical approach that allows us to treat the long-time behavior of the recalling process in an oscillator neural network. It is well known that in coupled oscillatory neuronal systems, under suitable conditions, the original dynamics can be reduced to a simpler phase dynamics. In this description, the phases of the oscillators can be regarded as the timings of the neuronal spikes. To attempt an analytical treatment of the recalling dynamics of such a system, we study a simplified model in which we discretize time and assume a synchronous updating rule. The theoretical results show that the retrieval dynamics is described by recursion equations for some macroscopic parameters, such as an overlap with the retrieval pattern. We then treat the noise components in the local field, which arise from the learning of the unretrieved patterns, as gaussian variables. However, we take account of the temporal correlation between these noise components at different times. In particular, we find that this correlation is essential for correctly predicting the behavior of the retrieval process in the case of autoassociative memory. From the derived equations, the maximal storage capacity and the basin of attraction are calculated and graphically displayed. We also consider the more general case that the network retrieves an ordered sequence of phase patterns. In both cases, the basin of attraction remains sufficiently wide to recall the memorized pattern from a noisy one, even near saturation. The validity of these theoretical results is supported by numerical simulations. We believe that this model serves as a convenient starting point for the theoretical study of retrieval dynamics in general oscillatory systems.

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

[2]  H. Nishimori,et al.  Retrieval dynamics of associative memory of the Hopfield type , 1993 .

[3]  M. Shiino,et al.  Self-consistent signal-to-noise analysis and its application to analogue neural networks with asymmetric connections , 1992 .

[4]  Toshio Aoyagi,et al.  OSCILLATOR NEURAL NETWORK RETRIEVING SPARSELY CODED PHASE PATTERNS , 1999 .

[5]  Joachim M. Buhmann,et al.  Pattern Segmentation in Associative Memory , 1990, Neural Computation.

[6]  Alex Arenas,et al.  Phase Locking in a Network of Neural Oscillators , 1994 .

[7]  Sompolinsky,et al.  Cooperative dynamics in visual processing. , 1991, Physical review. A, Atomic, molecular, and optical physics.

[8]  A. Noest.  Associative Memory in Sparse Phasor Neural Networks , 1988 .

[9]  E. Izhikevich,et al.  Weakly connected neural networks , 1997 .

[10]  Yoshiki Kuramoto,et al.  Chemical Oscillations, Waves, and Turbulence , 1984, Springer Series in Synergetics.

[11]  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.

[12]  Tomoki Fukai,et al.  Memory Recall by Quasi-Fixed-Point Attractors in Oscillator Neural Networks , 1995, Neural Computation.

[13]  W. Singer,et al.  Oscillatory responses in cat visual cortex exhibit inter-columnar synchronization which reflects global stimulus properties , 1989, Nature.

[14]  E. Gardner,et al.  Zero temperature parallel dynamics for infinite range spin glasses and neural networks , 1987 .

[15]  J Cook,et al.  The mean-field theory of a Q-state neural network model , 1989 .

[16]  Shun-ichi Amari.  Associative Memory and Its Statistical Neurodynamical Analysis , 1988 .

[17]  John J. Hopfield,et al.  Neural networks and physical systems with emergent collective computational abilities , 1999 .

[18]  Masato Okada,et al.  A hierarchy of macrodynamical equations for associative memory , 1995, Neural Networks.

[19]  Synchronization in a network of neuronal oscillators with finite storage capacity. , 1995, Physical review. E, Statistical physics, plasmas, fluids, and related interdisciplinary topics.

[20]  Sherrington,et al.  Dynamics of fully connected attractor neural networks near saturation. , 1993, Physical review letters.

[21]  Deliang Wang,et al.  Global competition and local cooperation in a network of neural oscillators , 1995 .

[22]  W. Kinzel,et al.  Layered neural networks , 1989 .

[23]  T. Aoyagi.  A Network of Oscillators for Retrieving Phase Information , 1994 .

[24]  Katsunori Kitano,et al.  EFFECT OF RANDOM SYNAPTIC DILUTION IN OSCILLATOR NEURAL NETWORKS , 1997 .

[25]  Nancy Kopell,et al.  Waves and synchrony in networks of oscillators of relaxation and non-relaxation type , 1995 .

[26]  Shun-ichi Amari,et al.  Learning Patterns and Pattern Sequences by Self-Organizing Nets of Threshold Elements , 1972, IEEE Transactions on Computers.

[27]  Shun-ichi Amari,et al.  Statistical neurodynamics of associative memory , 1988, Neural Networks.

[28]  Aoyagi,et al.  Network of Neural Oscillators for Retrieving Phase Information. , 1994, Physical review letters.