# Linear Constraints Learning for Spiking Neurons

arXiv: https://arxiv.org/abs/2103.12564 · HTML: https://mlsanity.com/paper/2103.12564/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 55 references that are in the map.
- First posted on arXiv 10 Mar 2021.

## Builds on (most cited first, 7 of 7)

- [Deep Learning in Spiking Neural Networks](https://mlsanity.com/paper/1804.08150/) (2018)
- [BP-STDP: Approximating Backpropagation using Spike Timing Dependent Plasticity](https://mlsanity.com/paper/1711.04214/) (2017)
- [Mapping Spiking Neural Networks to Neuromorphic Hardware](https://mlsanity.com/paper/1909.01843/) (2019)
- [Which spike train distance is most suitable for distinguishing rate and temporal coding?](https://mlsanity.com/paper/1708.07508/) (2017)
- [Design and implementation of a modular interior-point solver for linear optimization](https://mlsanity.com/paper/2006.08814/) (2020)
- [Supervised Learning in Spiking Neural Networks for Precise Temporal Encoding](https://mlsanity.com/paper/1601.03649/) (2016)
- [Supervised Learning with First-to-Spike Decoding in Multilayer Spiking Neural Networks](https://mlsanity.com/paper/2008.06937/) (2020)

## Abstract (arXiv)

We introduce a new supervised learning algorithm based to train spiking neural networks for classification. The algorithm overcomes a limitation of existing multi-spike learning methods: it solves the problem of interference between interacting output spikes during a learning trial. This problem of learning interference causes learning performance in existing approaches to decrease as the number of output spikes increases, and represents an important limitation in existing multi-spike learning approaches. We address learning interference by introducing a novel mechanism to balance the magnitudes of weight adjustments during learning, which in theory allows every spike to simultaneously converge to their desired timings. Our results indicate that our method achieves significantly higher memory capacity and faster convergence compared to existing approaches for multi-spike classification. In the ubiquitous Iris and MNIST datasets, our algorithm achieves competitive predictive performance with state-of-the-art approaches.