# Revisiting Gaussian Neurons for Online Clustering with Unknown Number of Clusters

arXiv: https://arxiv.org/abs/2205.00920 · HTML: https://mlsanity.com/paper/2205.00920/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 29 references that are in the map.
- First posted on arXiv 2 May 2022.

## Builds on (most cited first, 6 of 6)

- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [Towards Biologically Plausible Deep Learning](https://mlsanity.com/paper/1502.04156/) (2015)
- [Unsupervised Learning by Competing Hidden Units](https://mlsanity.com/paper/1806.10181/) (2018)
- [Local Unsupervised Learning for Image Analysis](https://mlsanity.com/paper/1908.08993/) (2019)
- [A Hebbian/Anti-Hebbian Network Derived from Online Non-Negative Matrix Factorization Can Cluster and Discover Sparse Features](https://mlsanity.com/paper/1503.00680/) (2015)
- [PyTorch-Hebbian: facilitating local learning in a deep learning framework](https://mlsanity.com/paper/2102.00428/) (2021)

## Built on by (most cited first, 1 of 1)

- [Online Arbitrary Shaped Clustering through Correlated Gaussian Functions](https://mlsanity.com/paper/2302.06335/) (2023)

## Abstract (arXiv)

Despite the recent success of artificial neural networks, more biologically plausible learning methods may be needed to resolve the weaknesses of backpropagation trained models such as catastrophic forgetting and adversarial attacks. Although these weaknesses are not specifically addressed, a novel local learning rule is presented that performs online clustering with an upper limit on the number of clusters to be found rather than a fixed cluster count. Instead of using orthogonal weight or output activation constraints, activation sparsity is achieved by mutual repulsion of lateral Gaussian neurons ensuring that multiple neuron centers cannot occupy the same location in the input domain. An update method is also presented for adjusting the widths of the Gaussian neurons in cases where the data samples can be represented by means and variances. The algorithms were applied on the MNIST and CIFAR-10 datasets to create filters capturing the input patterns of pixel patches of various sizes. The experimental results demonstrate stability in the learned parameters across a large number of training samples.