# PyTorch-Hebbian: facilitating local learning in a deep learning framework

arXiv: https://arxiv.org/abs/2102.00428 · HTML: https://mlsanity.com/paper/2102.00428/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 20 references that are in the map.
- First posted on arXiv 31 Jan 2021.

## Builds on (most cited first, 4 of 4)

- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [Unsupervised Learning by Competing Hidden Units](https://mlsanity.com/paper/1806.10181/) (2018)
- [A Hebbian/Anti-Hebbian Neural Network for Linear Subspace Learning: A Derivation from Multidimensional Scaling of Streaming Data](https://mlsanity.com/paper/1503.00669/) (2015)
- [Local Unsupervised Learning for Image Analysis](https://mlsanity.com/paper/1908.08993/) (2019)

## Built on by (most cited first, 2 of 2)

- [Revisiting Gaussian Neurons for Online Clustering with Unknown Number of Clusters](https://mlsanity.com/paper/2205.00920/) (2022)
- [Self-Motivated Growing Neural Network for Adaptive Architecture via Local Structural Plasticity](https://mlsanity.com/paper/2512.12713/) (2025)

## Abstract (arXiv)

Recently, unsupervised local learning, based on Hebb's idea that change in synaptic efficacy depends on the activity of the pre- and postsynaptic neuron only, has shown potential as an alternative training mechanism to backpropagation. Unfortunately, Hebbian learning remains experimental and rarely makes it way into standard deep learning frameworks. In this work, we investigate the potential of Hebbian learning in the context of standard deep learning workflows. To this end, a framework for thorough and systematic evaluation of local learning rules in existing deep learning pipelines is proposed. Using this framework, the potential of Hebbian learned feature extractors for image classification is illustrated. In particular, the framework is used to expand the Krotov-Hopfield learning rule to standard convolutional neural networks without sacrificing accuracy compared to end-to-end backpropagation. The source code is available at https://github.com/Joxis/pytorch-hebbian.