# Ultra-low-power Image Classification on Neuromorphic Hardware

arXiv: https://arxiv.org/abs/2309.16795 · HTML: https://mlsanity.com/paper/2309.16795/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 33 references that are in the map.
- First posted on arXiv 28 Sep 2023.

## Builds on (most cited first, 12 of 12)

- [Going Deeper in Spiking Neural Networks: VGG and Residual Architectures](https://mlsanity.com/paper/1802.02627/) (2018)
- [Optimal ANN-SNN Conversion for High-accuracy and Ultra-low-latency Spiking Neural Networks](https://mlsanity.com/paper/2303.04347/) (2023)
- [T2FSNN: Deep Spiking Neural Networks with Time-to-first-spike Coding](https://mlsanity.com/paper/2003.11741/) (2020)
- [Fast and Efficient Information Transmission with Burst Spikes in Deep Spiking Neural Networks](https://mlsanity.com/paper/1809.03142/) (2018)
- [Theory and Tools for the Conversion of Analog to Spiking Convolutional Neural Networks](https://mlsanity.com/paper/1612.04052/) (2016)
- [An Efficient Spiking Neural Network for Recognizing Gestures with a DVS Camera on the Loihi Neuromorphic Processor](https://mlsanity.com/paper/2006.09985/) (2020)
- [Spiking Deep Residual Network](https://mlsanity.com/paper/1805.01352/) (2018)
- [Algorithm and Hardware Design of Discrete-Time Spiking Neural Networks Based on Back Propagation with Binary Activations](https://mlsanity.com/paper/1709.06206/) (2017)
- [You Only Spike Once: Improving Energy-Efficient Neuromorphic Inference to ANN-Level Accuracy](https://mlsanity.com/paper/2006.09982/) (2020)
- [Recognizing Images with at most one Spike per Neuron](https://mlsanity.com/paper/2001.01682/) (2019)
- [Efficient Computation in Adaptive Artificial Spiking Neural Networks](https://mlsanity.com/paper/1710.04838/) (2017)
- [Optimized spiking neurons classify images with high accuracy through temporal coding with two spikes](https://mlsanity.com/paper/2002.00860/) (2020)

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

- [Modern Neuromorphic AI: From Intra-Token to Inter-Token Processing](https://mlsanity.com/paper/2601.00245/) (2026)
- [PrivSpike: Employing Homomorphic Encryption for Private Inference of Deep Spiking Neural Networks](https://mlsanity.com/paper/2510.03995/) (2025)
- [Discretized Quadratic Integrate-and-Fire Neuron Model for Deep Spiking Neural Networks](https://mlsanity.com/paper/2510.05168/) (2025)

## Abstract (arXiv)

Spiking neural networks (SNNs) promise ultra-low-power applications by exploiting temporal and spatial sparsity. The number of binary activations, called spikes, is proportional to the power consumed when executed on neuromorphic hardware. Training such SNNs using backpropagation through time for vision tasks that rely mainly on spatial features is computationally costly. Training a stateless artificial neural network (ANN) to then convert the weights to an SNN is a straightforward alternative when it comes to image recognition datasets. Most conversion methods rely on rate coding in the SNN to represent ANN activation, which uses enormous amounts of spikes and, therefore, energy to encode information. Recently, temporal conversion methods have shown promising results requiring significantly fewer spikes per neuron, but sometimes complex neuron models. We propose a temporal ANN-to-SNN conversion method, which we call Quartz, that is based on the time to first spike (TTFS). Quartz achieves high classification accuracy and can be easily implemented on neuromorphic hardware while using the least amount of synaptic operations and memory accesses. It incurs a cost of two additional synapses per neuron compared to previous temporal conversion methods, which are readily available on neuromorphic hardware. We benchmark Quartz on MNIST, CIFAR10, and ImageNet in simulation to show the benefits of our method and follow up with an implementation on Loihi, a neuromorphic chip by Intel. We provide evidence that temporal coding has advantages in terms of power consumption, throughput, and latency for similar classification accuracy. Our code and models are publicly available.