# Efficient Implementation of a Multi-Layer Gradient-Free Online-Trainable Spiking Neural Network on FPGA

arXiv: https://arxiv.org/abs/2305.19468 · HTML: https://mlsanity.com/paper/2305.19468/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 56 references that are in the map.
- First posted on arXiv 31 May 2023.

## Builds on (most cited first, 16 of 16)

- [Surrogate Gradient Learning in Spiking Neural Networks](https://mlsanity.com/paper/1901.09948/) (2019)
- [Event-based Vision meets Deep Learning on Steering Prediction for Self-driving Cars](https://mlsanity.com/paper/1804.01310/) (2018)
- [SuperSpike: Supervised learning in multi-layer spiking neural networks](https://mlsanity.com/paper/1705.11146/) (2017)
- [Long short-term memory and learning-to-learn in networks of spiking neurons](https://mlsanity.com/paper/1803.09574/) (2018)
- [Time-Ordered Recent Event (TORE) Volumes for Event Cameras](https://mlsanity.com/paper/2103.06108/) (2021)
- [Event-Based Backpropagation can compute Exact Gradients for Spiking Neural Networks](https://mlsanity.com/paper/2009.08378/) (2020)
- [Unsupervised Learning of a Hierarchical Spiking Neural Network for Optical Flow Estimation: From Events to Global Motion Perception](https://mlsanity.com/paper/1807.10936/) (2018)
- [Event-based Feature Extraction Using Adaptive Selection Thresholds](https://mlsanity.com/paper/1907.07853/) (2019)
- [First-spike based visual categorization using reward-modulated STDP](https://mlsanity.com/paper/1705.09132/) (2017)
- [Event-based Object Detection and Tracking for Space Situational Awareness](https://mlsanity.com/paper/1911.08730/) (2019)
- [Event-based Processing of Single Photon Avalanche Diode Sensors](https://mlsanity.com/paper/2001.02060/) (2019)
- [Acquisition of Visual Features Through Probabilistic Spike-Timing-Dependent Plasticity](https://mlsanity.com/paper/1606.01102/) (2016)
- [An optimised deep spiking neural network architecture without gradients](https://mlsanity.com/paper/2109.12813/) (2021)
- [Event-driven Spectrotemporal Feature Extraction and Classification using a Silicon Cochlea Model](https://mlsanity.com/paper/2212.07136/) (2022)
- [Racing to Learn: Statistical Inference and Learning in a Single Spiking Neuron with Adaptive Kernels](https://mlsanity.com/paper/1408.1245/) (2014)
- [Turn Down that Noise: Synaptic Encoding of Afferent SNR in a Single Spiking Neuron](https://mlsanity.com/paper/1411.2821/) (2014)

## Built on by (most cited first, 1 of 1)

- [Ultrafast On-Chip Online Learning via Spline Locality in Kolmogorov-Arnold Networks](https://mlsanity.com/paper/2602.02056/) (2026)

## Abstract (arXiv)

This paper presents an efficient hardware implementation of the recently proposed Optimized Deep Event-driven Spiking Neural Network Architecture (ODESA). ODESA is the first network to have end-to-end multi-layer online local supervised training without using gradients and has the combined adaptation of weights and thresholds in an efficient hierarchical structure. This research shows that the network architecture and the online training of weights and thresholds can be implemented efficiently on a large scale in hardware. The implementation consists of a multi-layer Spiking Neural Network (SNN) and individual training modules for each layer that enable online self-learning without using back-propagation. By using simple local adaptive selection thresholds, a Winner-Takes-All (WTA) constraint on each layer, and a modified weight update rule that is more amenable to hardware, the trainer module allocates neuronal resources optimally at each layer without having to pass high-precision error measurements across layers. All elements in the system, including the training module, interact using event-based binary spikes. The hardware-optimized implementation is shown to preserve the performance of the original algorithm across multiple spatial-temporal classification problems with significantly reduced hardware requirements.