Threshold Noise as a Source of Volatility in Random Synchronous Asymmetric Neural Networks

Simple item page
dc.creatorBohr, Henrik
dc.creatorMcGuire, Patrick
dc.creatorPershing, Chris
dc.creatorRafelski, Johann
dc.date1997-12-12
dc.date.accessioned2026-07-07T03:09:37Z
dc.date.available2026-07-07T03:09:37Z
dc.descriptionWe study the diversity of complex spatio-temporal patterns of random synchronous asymmetric neural networks (RSANNs). Specifically, we investigate the impact of noisy thresholds on network performance and find that there is a narrow and interesting region of noise parameters where RSANNs display specific features of behavior desired for rapidly `thinking' systems: accessibility to a large set of distinct, complex patterns.
dc.description17 pages, 11 figures, submitted to Neural Computation
dc.identifierhttps://arxiv.org/abs/cond-mat/9712132
dc.identifierhttp://arxiv.org/abs/cond-mat/9712132
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/27957
dc.subjectDisordered Systems and Neural Networks
dc.subjectAdaptation and Self-Organizing Systems
dc.subjectBiological Physics
dc.subjectNeurons and Cognition
dc.titleThreshold Noise as a Source of Volatility in Random Synchronous Asymmetric Neural Networks
dc.typetext

Files

Collections

arXiv