# Spikemax: Spike-based Loss Methods for Classification

arXiv: https://arxiv.org/abs/2205.09845 · HTML: https://mlsanity.com/paper/2205.09845/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 May 2022.

## Built on by (most cited first, 3 of 3)

- [Beyond Rate Coding: Surrogate Gradients Enable Spike Timing Learning in Spiking Neural Networks](https://mlsanity.com/paper/2507.16043/) (2025)
- [Exploiting heterogeneous delays for efficient computation in low-bit neural networks](https://mlsanity.com/paper/2510.27434/) (2025)
- [Automated detection of Zika and dengue in Aedes aegypti using neural spiking analysis](https://mlsanity.com/paper/2312.08654/) (2023)

## Abstract (arXiv)

Spiking Neural Networks~(SNNs) are a promising research paradigm for low power edge-based computing. Recent works in SNN backpropagation has enabled training of SNNs for practical tasks. However, since spikes are binary events in time, standard loss formulations are not directly compatible with spike output. As a result, current works are limited to using mean-squared loss of spike count. In this paper, we formulate the output probability interpretation from the spike count measure and introduce spike-based negative log-likelihood measure which are more suited for classification tasks especially in terms of the energy efficiency and inference latency. We compare our loss measures with other existing alternatives and evaluate using classification performances on three neuromorphic benchmark datasets: NMNIST, DVS Gesture and N-TIDIGITS18. In addition, we demonstrate state of the art performances on these datasets, achieving faster inference speed and less energy consumption.