Scaling Equilibrium Propagation to Deep ConvNets by Drastically Reducing its Gradient Estimator Bias
Abstract
Equilibrium Propagation (EP) is a biologically-inspired counterpart of Backpropagation Through Time (BPTT) which, owing to its strong theoretical guarantees and the locality in space of its learning rule, fosters the design of energy-efficient hardware dedicated to learning. In practice, however, EP does not scale to visual tasks harder than MNIST. In this work, we show that a bias in the gradient estimate of EP, inherent in the use of finite nudging, is responsible for this phenomenon and that cancelling it allows training deep ConvNets by EP, including architectures with distinct forward and backward connections. These results highlight EP as a scalable approach to compute error gradients in deep neural networks, thereby motivating its hardware implementation.
Cite
@article{arxiv.2101.05536,
title = {Scaling Equilibrium Propagation to Deep ConvNets by Drastically Reducing its Gradient Estimator Bias},
author = {Axel Laborieux and Maxence Ernoult and Benjamin Scellier and Yoshua Bengio and Julie Grollier and Damien Querlioz},
journal= {arXiv preprint arXiv:2101.05536},
year = {2021}
}
Comments
NeurIPS 2020 Workshop : "Beyond Backpropagation Novel Ideas for Training Neural Architectures". arXiv admin note: substantial text overlap with arXiv:2006.03824