# Advancing the Biological Plausibility and Efficacy of Hebbian Convolutional Neural Networks

arXiv: https://arxiv.org/abs/2501.17266 · HTML: https://mlsanity.com/paper/2501.17266/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 64 references that are in the map.
- First posted on arXiv 6 Jan 2025.

## Builds on (most cited first, 16 of 16)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification](https://mlsanity.com/paper/1502.01852/) (2015)
- [UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction](https://mlsanity.com/paper/1802.03426/) (2018)
- [Xception: Deep Learning with Depthwise Separable Convolutions](https://mlsanity.com/paper/1610.02357/) (2016)
- [A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attacks](https://mlsanity.com/paper/1807.03888/) (2018)
- [The Forward-Forward Algorithm: Some Preliminary Investigations](https://mlsanity.com/paper/2212.13345/) (2022)
- [Unsupervised Learning by Competing Hidden Units](https://mlsanity.com/paper/1806.10181/) (2018)
- [SoftHebb: Bayesian Inference in Unsupervised Hebbian Soft Winner-Take-All Networks](https://mlsanity.com/paper/2107.05747/) (2021)
- [Hebbian learning with gradients: Hebbian convolutional neural networks with modern deep learning frameworks](https://mlsanity.com/paper/2107.01729/) (2021)
- [Local Unsupervised Learning for Image Analysis](https://mlsanity.com/paper/1908.08993/) (2019)
- [FastHebb: Scaling Hebbian Training of Deep Neural Networks to ImageNet Level](https://mlsanity.com/paper/2207.03172/) (2022)
- [Is Bio-Inspired Learning Better than Backprop? Benchmarking Bio Learning vs. Backprop](https://mlsanity.com/paper/2212.04614/) (2022)
- [Synaptic Plasticity Models and Bio-Inspired Unsupervised Deep Learning: A Survey](https://mlsanity.com/paper/2307.16236/) (2023)
- [Neural Echos: Depthwise Convolutional Filters Replicate Biological Receptive Fields](https://mlsanity.com/paper/2401.10178/) (2024)
- [Photons guided by axons may enable backpropagation-based learning in the brain](https://mlsanity.com/paper/2203.11135/) (2022)
- [Deep Continuous Networks](https://mlsanity.com/paper/2402.01557/) (2024)

## Built on by (most cited first, 4 of 4)

- [Stochastic Forward-Forward Learning through Representational Dimensionality Compression](https://mlsanity.com/paper/2505.16649/) (2025)
- [NM-Hebb: Coupling Local Hebbian Plasticity with Metric Learning for More Accurate and Interpretable CNNs](https://mlsanity.com/paper/2508.19896/) (2025)
- [Hebbian Learning with Global Direction](https://mlsanity.com/paper/2601.21367/) (2026)
- [Minimizing the Effect of Sleep Deprivation in the Forward-Forward Algorithm](https://mlsanity.com/paper/2609.06042/) (2026)

## Abstract (arXiv)

The research presented in this paper advances the integration of Hebbian learning into Convolutional Neural Networks (CNNs) for image processing, systematically exploring different architectures to build an optimal configuration, adhering to biological tenability. Hebbian learning operates on local unsupervised neural information to form feature representations, providing an alternative to the popular but arguably biologically implausible and computationally intensive backpropagation learning algorithm. The suggested optimal architecture significantly enhances recent research aimed at integrating Hebbian learning with competition mechanisms and CNNs, expanding their representational capabilities by incorporating hard Winner-Takes-All (WTA) competition, Gaussian lateral inhibition mechanisms, and Bienenstock-Cooper-Munro (BCM) learning rule in a single model. Mean accuracy classification measures during the last half of test epochs on CIFAR-10 revealed that the resulting optimal model matched its end-to-end backpropagation variant with 75.2% each, critically surpassing the state-of-the-art hard-WTA performance in CNNs of the same network depth (64.6%) by 10.6%. It also achieved competitive performance on MNIST (98%) and STL-10 (69.5%). Moreover, results showed clear indications of sparse hierarchical learning through increasingly complex and abstract receptive fields. In summary, our implementation enhances both the performance and the generalisability of the learnt representations and constitutes a crucial step towards more biologically realistic artificial neural networks.