Parallel Hopfield Networks

We introduce a novel type of neural network, termed the parallel Hopfield network, that can simultaneously effect the dynamics of many different, independent Hopfield networks in parallel in the same piece of neural hardware. Numerically we find that under certain conditions, each Hopfield subnetwork has a finite memory capacity approaching that of the equivalent isolated attractor network, while a simple signal-to-noise analysis sheds qualitative, and some quantitative, insight into the workings (and failures) of the system.

[1]  J. Eccles.  The Physiology of Synapses , 1964, Springer Berlin Heidelberg.

[2]  J. Buhmann,et al.  Associative memory with high information content. , 1989, Physical review. A, General physics.

[3]  Z. Nadasdy,et al.  Neurons of the cerebral cortex exhibit precise interspike timing in correspondence to behavior. , 2005, Proceedings of the National Academy of Sciences of the United States of America.

[4]  Yuji Ikegaya,et al.  Synfire Chains and Cortical Songs: Temporal Modules of Cortical Activity , 2004, Science.

[5]  David J. Foster,et al.  Reverse replay of behavioural sequences in hippocampal place cells during the awake state , 2006, Nature.

[6]  Ad Aertsen,et al.  Stable propagation of synchronous spiking in cortical neural networks , 1999, Nature.

[7]  N. Spruston,et al.  Action potential initiation and backpropagation in neurons of the mammalian CNS , 1997, Trends in Neurosciences.

[8]  Moshe Abeles,et al.  Corticonics: Neural Circuits of Cerebral Cortex , 1991 .

[9]  M. Tsodyks,et al.  The Enhanced Storage Capacity in Neural Networks with Low Activity Level , 1988 .

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

[11]  Eugene M. Izhikevich,et al.  Polychronization: Computation with Spikes , 2006, Neural Computation.

[12]  Neil Burgess,et al.  Attractor Dynamics in the Hippocampal Representation of the Local Environment , 2005, Science.

[13]  Sebastian A. Wills,et al.  Computation with Spiking Neurons , 2004 .

[14]  J. Leo van Hemmen,et al.  Statistical Mechanics of Temporal Association in Neural Networks , 1990, NIPS.

[15]  J. Magee,et al.  State-Dependent Dendritic Computation in Hippocampal CA1 Pyramidal Neurons , 2006, The Journal of Neuroscience.

[16]  Sompolinsky,et al.  Neural networks with nonlinear synapses and a static noise. , 1986, Physical review. A, General physics.

[17]  M. Meister.  Multineuronal codes in retinal signaling. , 1996, Proceedings of the National Academy of Sciences of the United States of America.

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

[19]  B. L. Ginsborg.  THE PHYSIOLOGY OF SYNAPSES , 1964 .