Work

Response functions improving performance in analog attractor neural networks

Year: 1994

Type: article

Abstract: In the context of attractor neural networks, we study how the equilibrium analog neural activities, reached by the network dynamics during memory retrieval, may improve storage performance by reducing the interferences between the recalled pattern and the other stored ones. We determine a simple dynamics that stabilizes network states hwich are highly correlated with the retrieved pattern, for a number of stored memories that does not exceed ${\mathrm{\ensuremath{\alpha}}}_{\mathit{a}\mathit{s}\mathit{t}}$N, where ${\mathrm{\ensuremath{\alpha}}}_{\mathit{a}\mathit{s}\mathit{t}}$\ensuremath{\in}[0,0.41] depends on the global activity level in the network and N is the number of neurons.

Source: Physical review. E, Statistical physics, plasmas, fluids, and related interdisciplinary topics

DOI: 10.1103/physreve.49.r1823

Authors: Nicolas Brunel, Riccardo Zecchina

Institutions: Istituto Nazionale di Fisica Nucleare, Istituto Nazionale di Fisica Nucleare, Sezione di Torino, University of Turin

Language: English

Topic: Neural Networks and Applications

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

OpenAlex ID: W1984267376

FWCI: 1.528

Cites: 12

Cited by: 10

Related to: 10