Multimodal transistors as ReLU activation functions in physical neural network classifiers - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue Scientific Reports Année : 2022

Multimodal transistors as ReLU activation functions in physical neural network classifiers

Résumé

Artificial neural networks (ANNs) providing sophisticated, power-efficient classification are finding their way into thin-film electronics. Thin-film technologies require robust, layout-efficient devices with facile manufacturability. Here, we show how the multimodal transistor's (MMT's) transfer characteristic, with linear dependence in saturation, replicates the rectified linear unit (ReLU) activation function of convolutional ANNs (CNNs). Using MATLAB, we evaluate CNN performance using systematically distorted ReLU functions, then substitute measured and simulated MMT transfer characteristics as proxies for ReLU. High classification accuracy is maintained, despite large variations in geometrical and electrical parameters, as CNNs use the same activation functions for training and classification.
Fichier principal
Vignette du fichier
s41598-021-04614-9.pdf (1.2 Mo) Télécharger le fichier
Origine : Fichiers éditeurs autorisés sur une archive ouverte

Dates et versions

hal-03552794 , version 1 (02-02-2022)

Licence

Paternité

Identifiants

Citer

Isin Surekcigil Pesch, Eva Bestelink, Olivier de Sagazan, Adnan Mehonic, Radu A. Sporea. Multimodal transistors as ReLU activation functions in physical neural network classifiers. Scientific Reports, 2022, 12 (1), ⟨10.1038/s41598-021-04614-9⟩. ⟨hal-03552794⟩
27 Consultations
48 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More