Forward Learning with Top-Down Feedback: Empirical and Analytical Characterization
Abstract
"Forward-only" algorithms, which train neural networks while avoiding a backward pass, have recently gained attention as a way of solving the biologically unrealistic aspects of backpropagation. Here, we first address compelling challenges related to the "forward-only" rules, which include reducing the performance gap with backpropagation and providing an analytical understanding of their dynamics. To this end, we show that the forward-only algorithm with top-down feedback is well-approximated by an "adaptive-feedback-alignment" algorithm, and we analytically track its performance during learning in a prototype high-dimensional setting. Then, we compare different versions of forward-only algorithms, focusing on the Forward-Forward and PEPITA frameworks, and we show that they share the same learning principles. Overall, our work unveils the connections between three key neuro-inspired learning rules, providing a link between "forward-only" algorithms, i.e., Forward-Forward and PEPITA, and an approximation of backpropagation, i.e., Feedback Alignment.
Cite
@article{arxiv.2302.05440,
title = {Forward Learning with Top-Down Feedback: Empirical and Analytical Characterization},
author = {Ravi Srinivasan and Francesca Mignacco and Martino Sorbaro and Maria Refinetti and Avi Cooper and Gabriel Kreiman and Giorgia Dellaferrera},
journal= {arXiv preprint arXiv:2302.05440},
year = {2024}
}