Effect in the spectra of eigenvalues and dynamics of RNNs trained with excitatory-inhibitory constraint.
Cogn Neurodyn
; 18(3): 1323-1335, 2024 Jun.
Article
em En
| MEDLINE
| ID: mdl-38826641
ABSTRACT
In order to comprehend and enhance models that describes various brain regions it is important to study the dynamics of trained recurrent neural networks. Including Dale's law in such models usually presents several challenges. However, this is an important aspect that allows computational models to better capture the characteristics of the brain. Here we present a framework to train networks using such constraint. Then we have used it to train them in simple decision making tasks. We characterized the eigenvalue distributions of the recurrent weight matrices of such networks. Interestingly, we discovered that the non-dominant eigenvalues of the recurrent weight matrix are distributed in a circle with a radius less than 1 for those whose initial condition before training was random normal and in a ring for those whose initial condition was random orthogonal. In both cases, the radius does not depend on the fraction of excitatory and inhibitory units nor the size of the network. Diminution of the radius, compared to networks trained without the constraint, has implications on the activity and dynamics that we discussed here. Supplementary Information The online version contains supplementary material available at 10.1007/s11571-023-09956-w.
Texto completo:
1
Coleções:
01-internacional
Base de dados:
MEDLINE
Idioma:
En
Revista:
Cogn Neurodyn
Ano de publicação:
2024
Tipo de documento:
Article
País de afiliação:
Argentina
País de publicação:
Holanda