Enhancing neural-network performance via assortativity
Journal Article
·
· Physical Review. E, Statistical, Nonlinear, and Soft Matter Physics (Print)
- Departamento de Electromagnetismo y Fisica de la Materia, and Institute Carlos I for Theoretical and Computational Physics, and Facultad de Ciencias, University of Granada, E-18071 Granada (Spain)
The performance of attractor neural networks has been shown to depend crucially on the heterogeneity of the underlying topology. We take this analysis a step further by examining the effect of degree-degree correlations - assortativity - on neural-network behavior. We make use of a method recently put forward for studying correlated networks and dynamics thereon, both analytically and computationally, which is independent of how the topology may have evolved. We show how the robustness to noise is greatly enhanced in assortative (positively correlated) neural networks, especially if it is the hub neurons that store the information.
- OSTI ID:
- 21560072
- Journal Information:
- Physical Review. E, Statistical, Nonlinear, and Soft Matter Physics (Print), Vol. 83, Issue 3; Other Information: DOI: 10.1103/PhysRevE.83.036114; (c) 2011 American Institute of Physics; ISSN 1539-3755
- Country of Publication:
- United States
- Language:
- English
Similar Records
Enhanced memory performance thanks to neural network assortativity
Adaptive activation functions accelerate convergence in deep and physics-informed neural networks
Adaptive Activation Functions Accelerate Convergence in Deep and Physics-informed Neural Networks
Journal Article
·
Thu Mar 24 00:00:00 EDT 2011
· AIP Conference Proceedings
·
OSTI ID:21560072
Adaptive activation functions accelerate convergence in deep and physics-informed neural networks
Journal Article
·
Mon Nov 25 00:00:00 EST 2019
· Journal of Computational Physics
·
OSTI ID:21560072
Adaptive Activation Functions Accelerate Convergence in Deep and Physics-informed Neural Networks
Journal Article
·
Sun Mar 01 00:00:00 EST 2020
· Journal of Computational Physics
·
OSTI ID:21560072