1201.5721 (J. F. Mejias et al.)

Short-term synaptic facilitation improves information retrieval in noisy
neural networks    [PDF]

J. F. Mejias, B. Hernandez-Gomez, J. J. Torres

Short-term synaptic depression and facilitation have been found to greatly
influence the performance of autoassociative neural networks. However, only
partial results, focused for instance on the computation of the maximum storage
capacity at zero temperature, have been obtained to date. In this work, we
extended the study of the effect of these synaptic mechanisms on
autoassociative neural networks to more realistic and general conditions,
including the presence of noise in the system. In particular, we characterized
the behavior of the system by means of its phase diagrams, and we concluded
that synaptic facilitation significantly enlarges the region of good retrieval
performance of the network. We also found that networks with facilitating
synapses may have critical temperatures substantially higher than those of
standard autoassociative networks, thus allowing neural networks to perform
better under high-noise conditions.

View original: http://arxiv.org/abs/1201.5721