Saved in:
Bibliographic Details
Main Authors: Bacvanski, Marc Gong, Ziyin, Liu, Poggio, Tomaso
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2510.18808
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908857929826304
author Bacvanski, Marc Gong
Ziyin, Liu
Poggio, Tomaso
author_facet Bacvanski, Marc Gong
Ziyin, Liu
Poggio, Tomaso
contents Feedback alignment and related weight-transport-free algorithms are often proposed as biologically plausible alternatives to backpropagation, yet they are typically formulated in discrete phases with implicitly synchronized forward and error signals. We develop a continuous-time model of feedback-alignment-type learning in which neural activities and synaptic weights evolve together under coupled first-order dynamics with distinct propagation, plasticity, and decay time constants. We show that learning is governed by the temporal overlap between presynaptic drive and a locally projected error signal, providing an analytic explanation for robustness to moderate timing mismatch and for failure when mismatch eliminates overlap. Our results show that in order for feedback-alignment-type algorithms to work at biological timescales, they must obey the same temporal overlap principle that applies to other biological processes like eligibility traces.
format Preprint
id arxiv_https___arxiv_org_abs_2510_18808
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Does Feedback Alignment Work at Biological Timescales?
Bacvanski, Marc Gong
Ziyin, Liu
Poggio, Tomaso
Machine Learning
Neurons and Cognition
Feedback alignment and related weight-transport-free algorithms are often proposed as biologically plausible alternatives to backpropagation, yet they are typically formulated in discrete phases with implicitly synchronized forward and error signals. We develop a continuous-time model of feedback-alignment-type learning in which neural activities and synaptic weights evolve together under coupled first-order dynamics with distinct propagation, plasticity, and decay time constants. We show that learning is governed by the temporal overlap between presynaptic drive and a locally projected error signal, providing an analytic explanation for robustness to moderate timing mismatch and for failure when mismatch eliminates overlap. Our results show that in order for feedback-alignment-type algorithms to work at biological timescales, they must obey the same temporal overlap principle that applies to other biological processes like eligibility traces.
title Does Feedback Alignment Work at Biological Timescales?
topic Machine Learning
Neurons and Cognition
url https://arxiv.org/abs/2510.18808