Unsupervised Local Plasticity in a Multi-Frequency VisNet Hierarchy

TL;DR

This paper presents an unsupervised, biologically inspired hierarchical visual system that learns from raw data using local plasticity rules, achieving competitive accuracy on CIFAR datasets without backpropagation.

Contribution

It introduces a novel local plasticity-based learning system that rivals some backpropagation methods in unsupervised visual representation learning.

Findings

Achieves 80.1% accuracy on CIFAR-10 with local plasticity.

Outperforms Hebbian-only baseline and fixed architecture reaches 61.4% on CIFAR-10.

Plasticity mechanisms significantly contribute to learned representations.

Abstract

We introduce an unsupervised visual representation learning system based entirely on local plasticity rules, without labels, backpropagation, or global error signals. The model is a VisNet-inspired hierarchical architecture combining opponent color inputs, multi-frequency Gabor and wavelet feature streams, competitive normalization with lateral inhibition, saliency modulation, associative memory, and a feedback loop. All representation learning occurs through continuous local plasticity applied to unlabeled image streams over 300 epochs. Performance is evaluated using a fixed linear probe trained only at readout time. The system achieves 80.1 percent accuracy on CIFAR-10 and 47.6 percent on CIFAR-100, improving over a Hebbian-only baseline. Ablation studies show that anti-Hebbian decorrelation, free-energy inspired plasticity, and associative memory are the main contributors, with strong synergistic effects. Even without learning, the fixed architecture alone reaches 61.4 percent on CIFAR-10, indicating that plasticity, not only inductive bias, drives most of the performance. Control analyses show that independently trained probes match co-trained ones within 0.3 percentage points, and a nearest-class-mean classifier achieves 78.3 percent without gradient-based training, confirming the intrinsic structure of the learned features. Overall, the system narrows but does not eliminate the performance gap to backpropagation-trained CNNs (5.7 percentage points on CIFAR-10, 7.5 percentage points on CIFAR-100), demonstrating that structured local plasticity alone can learn strong visual representations from raw unlabeled data.