LGNEMay 22, 2025

Stochastic Forward-Forward Learning through Representational Dimensionality Compression

arXiv:2505.16649v33 citationsh-index: 5Has Code
Originality Incremental advance
AI Analysis

This work addresses the need for more biologically plausible learning algorithms, with potential applications in neuromorphic computing, though it is incremental as it builds on existing Forward-Forward methods.

The paper tackled the problem of designing a biologically plausible alternative to backpropagation by proposing a novel goodness function based on effective dimensionality for the Forward-Forward algorithm, achieving competitive performance with other non-backpropagation methods.

The Forward-Forward (FF) learning algorithm provides a bottom-up alternative to backpropagation (BP) for training neural networks, relying on a layer-wise "goodness" function with well-designed negative samples for contrastive learning. Existing goodness functions are typically defined as the sum of squared postsynaptic activations, neglecting correlated variability between neurons. In this work, we propose a novel goodness function termed dimensionality compression that uses the effective dimensionality (ED) of fluctuating neural responses to incorporate second-order statistical structure. Our objective minimizes ED for noisy copies of individual inputs while maximizing it across the sample distribution, promoting structured representations without the need to prepare negative samples.We demonstrate that this formulation achieves competitive performance compared to other non-BP methods. Moreover, we show that noise plays a constructive role that can enhance generalization and improve inference when predictions are derived from the mean of squared output, which is equivalent to making predictions based on an energy term. Our findings contribute to the development of more biologically plausible learning algorithms and suggest a natural fit for neuromorphic computing, where stochasticity is a computational resource rather than a nuisance. The code is available at https://github.com/ZhichaoZhu/StochasticForwardForward

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes