Associative Memory and Segmentation in a Network Composed of Izhikevich Neurons

Associative memory is one of the brain's main function. This paper presents a new artificial neural network composed of Izhikevich neuron models to simulate the associative memory and segmentation of human brain. The stored memory patterns are coded with the connection weight. The memory is represented in the spatio-temporal firing pattern of the neurons. The stored memory patterns can be retrieved and segmented through the adjusting of connection weight when the network is presented with corrupted input patterns. The simulation results prove that connection weight plays an important role in the associative memory and segmentation of human brain, by changing the connection weight the neural network can implement the associative memory and segmentation functions of human brain.

[1]  Eugene M. Izhikevich,et al.  Simple model of spiking neurons , 2003, IEEE Trans. Neural Networks.

[2]  E. Capaldi,et al.  The organization of behavior. , 1992, Journal of applied behavior analysis.

[3]  Thomas Wennekers,et al.  Associative memory in networks of spiking neurons , 2001, Neural Networks.

[4]  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.

[5]  Martin Rehn,et al.  Storing and restoring visual input with collaborative rank coding and associative memory , 2006, Neurocomputing.

[6]  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.

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