# Multi-Sample Online Learning for Spiking Neural Networks based on Generalized Expectation Maximization

arXiv: https://arxiv.org/abs/2102.03280 · HTML: https://mlsanity.com/paper/2102.03280/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 27 references that are in the map.
- First posted on arXiv 5 Feb 2021.

## Builds on (most cited first, 11 of 11)

- [On Calibration of Modern Neural Networks](https://mlsanity.com/paper/1706.04599/) (2017)
- [Energy and Policy Considerations for Deep Learning in NLP](https://mlsanity.com/paper/1906.02243/) (2019)
- [Surrogate Gradient Learning in Spiking Neural Networks](https://mlsanity.com/paper/1901.09948/) (2019)
- [SuperSpike: Supervised learning in multi-layer spiking neural networks](https://mlsanity.com/paper/1705.11146/) (2017)
- [Benchmarking Keyword Spotting Efficiency on Neuromorphic Hardware](https://mlsanity.com/paper/1812.01739/) (2018)
- [An Introduction to Probabilistic Spiking Neural Networks: Probabilistic Models, Learning Rules, and Applications](https://mlsanity.com/paper/1910.01059/) (2019)
- [A Brief Introduction to Machine Learning for Engineers](https://mlsanity.com/paper/1709.02840/) (2017)
- [VOWEL: A Local Online Learning Rule for Recurrent Networks of Probabilistic Spiking Winner-Take-All Circuits](https://mlsanity.com/paper/2004.09416/) (2020)
- [A learning framework for winner-take-all networks with stochastic synapses](https://mlsanity.com/paper/1708.04251/) (2017)
- [Spike Event Based Learning in Neural Networks](https://mlsanity.com/paper/1502.05777/) (2015)
- [Training Dynamic Exponential Family Models with Causal and Lateral Dependencies for Generalized Neuromorphic Computing](https://mlsanity.com/paper/1810.08940/) (2018)

## Abstract (arXiv)

Spiking Neural Networks (SNNs) offer a novel computational paradigm that captures some of the efficiency of biological brains by processing through binary neural dynamic activations. Probabilistic SNN models are typically trained to maximize the likelihood of the desired outputs by using unbiased estimates of the log-likelihood gradients. While prior work used single-sample estimators obtained from a single run of the network, this paper proposes to leverage multiple compartments that sample independent spiking signals while sharing synaptic weights. The key idea is to use these signals to obtain more accurate statistical estimates of the log-likelihood training criterion, as well as of its gradient. The approach is based on generalized expectation-maximization (GEM), which optimizes a tighter approximation of the log-likelihood using importance sampling. The derived online learning algorithm implements a three-factor rule with global per-compartment learning signals. Experimental results on a classification task on the neuromorphic MNIST-DVS data set demonstrate significant improvements in terms of log-likelihood, accuracy, and calibration when increasing the number of compartments used for training and inference.