# Locally Connected Spiking Neural Networks for Unsupervised Feature Learning

arXiv: https://arxiv.org/abs/1904.06269 · HTML: https://mlsanity.com/paper/1904.06269/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Apr 2019.

## Built on by (most cited first, 9 of 9)

- [Q-SpiNN: A Framework for Quantizing Spiking Neural Networks](https://mlsanity.com/paper/2107.01807/) (2021)
- [SpikeDyn: A Framework for Energy-Efficient Spiking Neural Networks with Continual and Unsupervised Learning Capabilities in Dynamic Environments](https://mlsanity.com/paper/2103.00424/) (2021)
- [lpSpikeCon: Enabling Low-Precision Spiking Neural Network Processing for Efficient Unsupervised Continual Learning on Autonomous Agents](https://mlsanity.com/paper/2205.12295/) (2022)
- [Mantis: Enabling Energy-Efficient Autonomous Mobile Agents with Spiking Neural Networks](https://mlsanity.com/paper/2212.12620/) (2022)
- [tinySNN: Towards Memory- and Energy-Efficient Spiking Neural Networks](https://mlsanity.com/paper/2206.08656/) (2022)
- [Models Developed for Spiking Neural Networks](https://mlsanity.com/paper/2212.04377/) (2022)
- [A survey on learning models of spiking neural membrane systems and spiking neural networks](https://mlsanity.com/paper/2403.18609/) (2024)
- [BioLCNet: Reward-modulated Locally Connected Spiking Neural Networks](https://mlsanity.com/paper/2109.05539/) (2021)
- [From Unimodal to Multimodal: improving sEMG-Based Pattern Recognition via deep generative models](https://mlsanity.com/paper/2308.04091/) (2023)

## Abstract (arXiv)

In recent years, Spiking Neural Networks (SNNs) have demonstrated great successes in completing various Machine Learning tasks. We introduce a method for learning image features by textitlocally connected layers in SNNs using spike-timing-dependent plasticity (STDP) rule. In our approach, sub-networks compete via competitive inhibitory interactions to learn features from different locations of the input space. These textitLocally-Connected SNNs (LC-SNNs) manifest key topological features of the spatial interaction of biological neurons. We explore biologically inspired n-gram classification approach allowing parallel processing over various patches of the the image space. We report the classification accuracy of simple two-layer LC-SNNs on two image datasets, which match the state-of-art performance and are the first results to date. LC-SNNs have the advantage of fast convergence to a dataset representation, and they require fewer learnable parameters than other SNN approaches with unsupervised learning. Robustness tests demonstrate that LC-SNNs exhibit graceful degradation of performance despite the random deletion of large amounts of synapses and neurons.