Efficient Associative Memory Based on a Nonlinear Function Constitution and Dynamic Synapses

Min Xia; Ying Cao Zhang; Xiao Ling Ye

doi:10.4028/www.scientific.net/AMR.225-226.479

Paper Titles

The Algorithm for Constructing Software Cost Estimation Model Based on Rough Set
p.461

Synchronization of Generalized Henon System via a Scalar Controller
p.465

Study on the Formation and Evolvement Mechanism of the Knowledge Service Network in the Agile Supply Chain
p.469

Intelligent Health Diagnosis Method for Aircraft Based on Multi-Source Information Fusion
p.475

Efficient Associative Memory Based on a Nonlinear Function Constitution and Dynamic Synapses
p.479

Research and Implementation of Conglutinated Macrophage Image Segmentation Based on Improved Watershed Algorithm
p.483

Distributed Information Fusion Structure Based on Data Fusion Tree
p.488

Applications of the Soave-Redlich-Kwong Equations of State Using Matlab
p.492

Control of Catalytic Divided Wall Column
p.496

HomeAdvanced Materials ResearchAdvanced Materials Research Vols. 225-226Efficient Associative Memory Based on a Nonlinear...

Efficient Associative Memory Based on a Nonlinear Function Constitution and Dynamic Synapses

Abstract:

Nonlinear function constitution and dynamic synapses, against spurious state for Hopfield neural network are proposed. The model of the dynamical connection weight and the updating scheme of the states of neurons are given. Nonlinear function constitution improves the conventional Hebbian learning rule with linear outer product method. Simulation results show that both nonlinear function constitution and dynamic synapses can effectively increase the ability of error tolerance; furthermore, associative memory of neural network with the new method can both enlarge attractive basin and increase storage capacity.

You might also be interested in these eBooks

Advanced Research on Automation, Communication, Architectonics and Materials

View Preview

Info:

Periodical:

Advanced Materials Research (Volumes 225-226)

Pages:

479-482

DOI:

https://doi.org/10.4028/www.scientific.net/AMR.225-226.479

Citation:

Cite this paper

Online since:

April 2011

Authors:

Min Xia, Ying Cao Zhang, Xiao Ling Ye

Keywords:

Associative Memory, Dynamic Synapses, Nonlinear Function Constitution, Spurious State

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

References

[1] J.J. Hopfield, neural networks and physical systems with emergent collective computation abilities, Proc. Nat. Acad. sci., USA Vol. 79 (1982), pp.2445-2558.

DOI: 10.1073/pnas.79.8.2554

Google Scholar

[2] O. Masato, Notions of associative memory and sparse coding, Neural Networks, Vol. 9 (1996), pp.1429-1458.

DOI: 10.1016/s0893-6080(96)00044-5

Google Scholar

[3] R. S. Armen, et al, A model synapse that incorporates properties of short- and long-term synaptic plasticity, Neural Networks Vol. 16 (2003), pp.1161-1177.

DOI: 10.1016/s0893-6080(03)00135-7

Google Scholar

[4] L F. Abbott, J.A. Varela, K. Sen, et a1., Synaptic Depression and Cortical Gain Control, Science, Vol. 275 (1997), pp.220-224.

DOI: 10.1126/science.275.5297.221

Google Scholar

[5] W. M. Kistler, Short-term Synaptic Plasticity and Network Behavior, Neural Computation Vol. 11(1999), pp.1579-1594.

DOI: 10.1162/089976699300016151

Google Scholar

[6] L. Abbott, W. G. Regehr, Synaptic computation, Nature Vol. 431 (2004), pp.796-803.

DOI: 10.1038/nature03010

Google Scholar

[7] A. Gruart, M.D. Muniz, Involvement of the CA3-CA1 synapse in the acquisition of associative learning in behaving mice, Journal of Neuroscience Vol. 26 (2006), pp.1077-1087.

DOI: 10.1523/jneurosci.2834-05.2006

Google Scholar

[8] M.V. Tsodyks, H. Markram, The neural code between neocortical pyramidal neurons depends on neurotransmitter release probability, Proc. Natl. Acad. Sci. USA Vol. 94 (1997), pp.719-723.

DOI: 10.1073/pnas.94.2.719

Google Scholar

[9] L. Pantic, J.J. Torres, and H.J. Kappen, Associative memory with dynamic synapses, Neural Computation Vol. 14 (2002), pp.2903-2923.

DOI: 10.1162/089976602760805331

Google Scholar