Error Forcing in Recurrent Neural Networks

A Erdem Sağtekin, Colin Bredenberg, Cristina Savin

Keywords: recurrent neural networks, bio-plausible learning

TL;DR: A more effective way of forcing RNN dynamics during supervised learning.

Abstract: How should feedback influence recurrent neural network (RNN) learning? One way to address the known limitations of backpropagation through time is to directly adjust neural activities during the learning process. However, it remains unclear how to effectively use feedback to shape RNN dynamics. Here, we introduce error forcing (EF), where the network activity is guided orthogonally toward the zero-error manifold during learning. This method contrasts with alternatives like teaching forcing, which impose stronger constraints on neural activity and thus induce larger feedback influence on circuit dynamics. Furthermore, EF can be understood from a Bayesian perspective as a form of approximate dynamic inference. Empirically, EF consistently outperforms other learning algorithms across several tasks and its benefits persist when additional biological constraints are taken into account. Overall, EF is a powerful temporal credit assignment mechanism and a promising candidate model for learning in biological systems.

Primary Area: Neuroscience and cognitive science (e.g., neural coding, brain-computer interfaces)

Submission Number: 24754