corner
corner
APS » Journals » Phys. Rev. Lett. » Volume 81 » Issue 13
< Previous Article | Next Article >

Phys. Rev. Lett. 81, 2827–2830 (1998)

Effect of Correlated Fluctuations of Synapses in the Performance of Neural Networks

Download: PDF (145 kB) Buy this article Export: BibTeX or EndNote (RIS)

J. Marro, P. L. Garrido, and J. J. Torres*
Institute “Carlos I” for Theoretical and Computational Physics, University of Granada, E-18071 Granada, Spain

Received 19 December 1997; published in the issue dated 28 September 1998

We consider stochastic neural networks in which synaptic intensities rapidly fluctuate—around means given by a learning rule—competing with neuron activity. Each snapshot of synaptic intensities contains the neuron-neuron correlations in one of the stored patterns chosen at random. The result is apparently noisy behavior which induces robustness, including improved associative and pattern recognition processes. The main result here might apply to biological systems that exhibit fluctuating patterns of synapses.

© 1998 The American Physical Society

URL:
http://link.aps.org/doi/10.1103/PhysRevLett.81.2827
DOI:
10.1103/PhysRevLett.81.2827
PACS:
87.10.+e, 05.40.+j, 75.10.Nr

*Present address: Institute for Nonlinear Science, University of California, San Diego, La Jolla, CA 92093-0402.

 
< Previous Article | Next Article >