Performance of Neural Clique Networks Subject to Synaptic Noise - Archive ouverte HAL Access content directly
Conference Papers Year : 2017

Performance of Neural Clique Networks Subject to Synaptic Noise

Abstract

Abstract-Artificial neural networks are so-called because they are supposed to be inspired from the brain and from the ways the neurons work. While some networks are used purely for computational purpose and do not endeavor to be a plausible representation of what happens in the brain, such as deep learning neural networks, others do. However, the question of the noise in the brain and its impact on the functioning of those networks has been little-studied. For example, it is widely known that synapses misfire with a significant probability. We model this noise and study its impact on associative memories powered by neural networks: neural clique networks and Hopfield networks as a reference point. We show that synaptic noise can in fact slightly improve the performance of the decoding process of neural clique networks by avoiding local minima.
Not file

Dates and versions

hal-01522729 , version 1 (15-05-2017)

Identifiers

  • HAL Id : hal-01522729 , version 1

Cite

Eliott Coyac, Vincent Gripon, Charlotte Langlais, Claude Berrou. Performance of Neural Clique Networks Subject to Synaptic Noise. COGNITIVE 2017 : The Ninth International Conference on Advanced Cognitive Technologies and Applications, Feb 2017, Athènes, Greece. pp.4 - 9. ⟨hal-01522729⟩
137 View
0 Download

Share

Gmail Facebook Twitter LinkedIn More