mlsanityData to 7 Oct 2026

Forward Direct Feedback Alignment for Online Gradient Estimates of Spiking Neural Networks

arXiv 2403.08804 ↗First posted 6 Feb 2024cs.NE cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

There is an interest in finding energy efficient alternatives to current state of the art neural network training algorithms. Spiking neural network are a promising approach, because they can be simulated energy efficiently on neuromorphic hardware platforms. However, these platforms come with limitations on the design of the training algorithm. Most importantly, backpropagation cannot be implemented on those. We propose a novel neuromorphic algorithm, the textitSpiking Forward Direct Feedback Alignment (SFDFA) algorithm, an adaption of textitForward Direct Feedback Alignment to train SNNs. SFDFA estimates the weights between output and hidden neurons as feedback connections. The main contribution of this paper is to describe how exact local gradients of spikes can be computed in an online manner while taking into account the intra-neuron dependencies between post-synaptic spikes and derive a dynamical system for neuromorphic hardware compatibility. We compare the SFDFA algorithm with a number of competitor algorithms and show that the proposed algorithm achieves higher performance and convergence rates.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 17 of its 34 references that are in the map. First posted on arXiv 6 Feb 2024.

Builds on

17 of 34 references.

References · 17

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
  3. 2017Spatio-Temporal Backpropagation for Training High-performance Spiking Neural Networkscited by 399
  4. 2020Going Deeper With Directly-Trained Larger Spiking Neural Networkscited by 268
  5. 2018SLAYER: Spike Layer Error Reassignment in Timecited by 257
  6. 2016Direct Feedback Alignment Provides Learning in Deep Neural Networkscited by 240
  7. 2019The Heidelberg spiking datasets for the systematic evaluation of spiking neural networkscited by 135
  8. 2016Supervised learning based on temporal coding in spiking neural networkscited by 75
  9. 2020Event-Based Backpropagation can compute Exact Gradients for Spiking Neural Networkscited by 59
  10. 2020Direct Feedback Alignment Scales to Modern Deep Learning Tasks and Architecturescited by 56
  11. 2019Fast and energy-efficient neuromorphic deep learning with first-spike timescited by 52
  12. 2018Decoupled Parallel Backpropagation with Convergence Guaranteecited by 39
5 more
  1. 2016Neuromorphic Deep Learning Machinescited by 38
  2. 2018Hybrid Macro/Micro Level Backpropagation for Training Deep Spiking Neural Networkscited by 30
  3. 2019Direct Feedback Alignment with Sparse Connections for Local Learningcited by 26
  4. 2021In-Hardware Learning of Multilayer Spiking Neural Networks on a Neuromorphic Processorcited by 11
  5. 2022Low-Variance Forward Gradients using Direct Feedback Alignment and Momentumcited by 7

Built on by

Not cited yet.