When Response Variability Increases Neural Network Robustness to Synaptic Noise

Details When Response Variability Increases Neural Network Robustness to Synaptic Noise When Response Variability Increases Neural Network Robustness to Synaptic Noise

2005-10-18

arxiv.org/abs/q-bio/0510036v1

Biology

Quantitative Biology

Neurons and Cognition

26 pages, 7 figures, to appear in Neural Computation

Scientific paper

Cortical sensory neurons are known to be highly variable, in the sense that responses evoked by identical stimuli often change dramatically from trial to trial. The origin of this variability is uncertain, but it is usually interpreted as detrimental noise that reduces the computational accuracy of neural circuits. Here we investigate the possibility that such response variability might, in fact, be beneficial, because it may partially compensate for a decrease in accuracy due to stochastic changes in the synaptic strengths of a network. We study the interplay between two kinds of noise, response (or neuronal) noise and synaptic noise, by analyzing their joint influence on the accuracy of neural networks trained to perform various tasks. We find an interesting, generic interaction: when fluctuations in the synaptic connections are proportional to their strengths (multiplicative noise), a certain amount of response noise in the input neurons can significantly improve network performance, compared to the same network without response noise. Performance is enhanced because response noise and multiplicative synaptic noise are in some ways equivalent. These results are demonstrated analytically for the most basic network consisting of two input neurons and one output neuron performing a simple classification task, but computer simulations show that the phenomenon persists in a wide range of architectures, including recurrent (attractor) networks and sensory-motor networks that perform coordinate transformations. The results suggest that response variability could play an important dynamic role in networks that continuously learn.

Affiliated with

Also associated with

No associations

Rating

When Response Variability Increases Neural Network Robustness to Synaptic Noise does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with When Response Variability Increases Neural Network Robustness to Synaptic Noise, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and When Response Variability Increases Neural Network Robustness to Synaptic Noise will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-242195