Toward Robust Analog Equilibrium Propagation by Investigating Power Calculation Dynamics - Equipe Circuits et Systèmes de Communications
Poster De Conférence Année : 2023

Toward Robust Analog Equilibrium Propagation by Investigating Power Calculation Dynamics

Résumé

In this work, we investigate the robustness and consistency of the Equilibrium Propagation (EqProp) algorithm for training analog neural networks, addressing previous research limitations. We analyze the algorithm's robustness concerning learning parameter variations and examine the relationship between power calculations and convergence behavior. By accounting for all relevant components and their impact on learning, we aim to develop a reliable and consistent algorithm based on EqProp principles.
Fichier principal
Vignette du fichier
2023_GDR_Kiraz.pdf (252.49 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04166116 , version 1 (19-07-2023)

Identifiants

  • HAL Id : hal-04166116 , version 1

Citer

Fatma Zulal Kiraz, Dang-Kièn Germain Pham, Patricia Desgreys. Toward Robust Analog Equilibrium Propagation by Investigating Power Calculation Dynamics. Colloque du GDR SOC2, Jun 2023, Lyon, France. 2023. ⟨hal-04166116⟩
137 Consultations
56 Téléchargements

Partager

More