Transient dynamics for sequence-processing neural networks: Effect of degree distributions

2007/05/31 by Yong Chen, Pan Zhang, Lianchun Yu +1
Computer Science · Neuroscience · Physics and Astronomy · #Neural Networks and Applications #Neural Networks and Reservoir Computing #Neural dynamics and brain function #cond-mat.dis-nn #cond-mat.stat-mech

paper · pdf · doi:10.1103/physreve.77.016110

published as Phys. Rev. E 77, 016110 (2008) · 11 pages, 6 figures

openalex publication_date 2008/01/29 · arxiv created 2008/01/31 · arxiv updated 2009/12/01 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

We derive an analytic evolution equation for overlap parameters, including the effect of degree distribution on the transient dynamics of sequence processing neural networks. In the special case of globally coupled networks, the precisely retrieved critical loading ratio alpha_c=N;-12 is obtained, where N is the network size. In the presence of random networks, our theoretical predictions agree quantitatively with the numerical experiments for delta, binomial, and power-law degree distributions.

Citations

• Emergence of scaling in random networks
• Performance of networks of artificial neurons: The role of clustering
• Statistical mechanics of neural networks near saturation
• An Exactly Solvable Asymmetric Neural Network Model
• On random graphs. I.