Energy-based analog neural network framework - LIRMM - Laboratoire d’Informatique, de Robotique et de Microélectronique de Montpellier Access content directly
Journal Articles Frontiers in Computational Neuroscience Year : 2023

Energy-based analog neural network framework

Mohamed Watfa
Alberto Garcia-Ortiz
Gilles Sassatelli

Abstract

Over the past decade a body of work has emerged and shown the disruptive potential of neuromorphic systems across a broad range of studies, often combining novel machine learning models and nanotechnologies. Still, the scope of investigations often remains limited to simple problems since the process of building, training, and evaluating mixed-signal neural models is slow and laborious. In this paper, we introduce an open-source framework, called EBANA, that provides a unified, modularized, and extensible infrastructure, similar to conventional machine learning pipelines, for building and validating analog neural networks (ANNs). It uses Python as interface language with a syntax similar to Keras, while hiding the complexity of the underlying analog simulations. It already includes the most common building blocks and maintains sufficient modularity and extensibility to easily incorporate new concepts, electrical, and technological models. These features make EBANA suitable for researchers and practitioners to experiment with different design topologies and explore the various tradeoffs that exist in the design space. We illustrate the framework capabilities by elaborating on the increasingly popular Energy-Based Models (EBMs), used in conjunction with the local Equilibrium Propagation (EP) training algorithm. Our experiments cover 3 datasets having up to 60,000 entries and explore network topologies generating circuits in excess of 1,000 electrical nodes that can be extensively benchmarked with ease and in reasonable time thanks to the native EBANA parallelization capability.
Fichier principal
Vignette du fichier
fncom-17-1114651.pdf (2.86 Mo) Télécharger le fichier
Origin Files produced by the author(s)
Licence

Dates and versions

lirmm-04306841 , version 1 (25-11-2023)

Licence

Identifiers

Cite

Mohamed Watfa, Alberto Garcia-Ortiz, Gilles Sassatelli. Energy-based analog neural network framework. Frontiers in Computational Neuroscience, 2023, 17, ⟨10.3389/fncom.2023.1114651⟩. ⟨lirmm-04306841⟩
20 View
17 Download

Altmetric

Share

Gmail Mastodon Facebook X LinkedIn More