A brain-inspired algorithm that mitigates catastrophic forgetting of artificial and spiking neural networks with low computational cost.
Sci Adv
; 9(34): eadi2947, 2023 08 25.
Article
em En
| MEDLINE
| ID: mdl-37624895
ABSTRACT
Neuromodulators in the brain act globally at many forms of synaptic plasticity, represented as metaplasticity, which is rarely considered by existing spiking (SNNs) and nonspiking artificial neural networks (ANNs). Here, we report an efficient brain-inspired computing algorithm for SNNs and ANNs, referred to here as neuromodulation-assisted credit assignment (NACA), which uses expectation signals to induce defined levels of neuromodulators to selective synapses, whereby the long-term synaptic potentiation and depression are modified in a nonlinear manner depending on the neuromodulator level. The NACA algorithm achieved high recognition accuracy with substantially reduced computational cost in learning spatial and temporal classification tasks. Notably, NACA was also verified as efficient for learning five different class continuous learning tasks with varying degrees of complexity, exhibiting a markedly mitigated catastrophic forgetting at low computational cost. Mapping synaptic weight changes showed that these benefits could be explained by the sparse and targeted synaptic modifications attributed to expectation-based global neuromodulation.
Texto completo:
1
Temas:
ECOS
/
Financiamentos_gastos
Bases de dados:
MEDLINE
Assunto principal:
Algoritmos
/
Redes Neurais de Computação
Tipo de estudo:
Health_economic_evaluation
/
Prognostic_studies
Idioma:
En
Revista:
Sci Adv
Ano de publicação:
2023
Tipo de documento:
Article
País de afiliação:
China