Generalization of stochastic-resonance-based threshold networks with Tikhonov regularization - Université d'Angers Accéder directement au contenu
Article Dans Une Revue Physical Review E Année : 2022

Generalization of stochastic-resonance-based threshold networks with Tikhonov regularization

Saiya Bai
Fabing Duan
Derek Abbott

Résumé

Injecting artificial noise into a feedforward threshold neural network allows it to become trainable by gradient-based methods and also enlarges the parameter space as well as the range of synaptic weights. This configuration constitutes a stochastic-resonance-based threshold neural network, where the noise level can adaptively converge to a nonzero optimal value for finding a local minimum of the loss criterion. We prove theoretically that the injected noise plays the role of a generalized Tikhonov regularizer for training the designed threshold network. Experiments on regression and classification problems demonstrate that the generalization of the stochastic-resonance-based threshold network is improved by the injection of noise. The feasibility of injecting noise into the threshold neural network opens up the potential for adaptive stochastic resonance in machine learning.
Fichier principal
Vignette du fichier
PhysRevE.106.L012101.pdf (700.65 Ko) Télécharger le fichier
Origine : Fichiers éditeurs autorisés sur une archive ouverte

Dates et versions

hal-03715996 , version 1 (23-01-2024)

Identifiants

Citer

Saiya Bai, Fabing Duan, François Chapeau-Blondeau, Derek Abbott. Generalization of stochastic-resonance-based threshold networks with Tikhonov regularization. Physical Review E , 2022, 106 (1), pp.L012101,1-5. ⟨10.1103/PhysRevE.106.L012101⟩. ⟨hal-03715996⟩
25 Consultations
5 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More