Smooth Exact Gradient Descent Learning in Spiking Neural Networks
Not on the map. Why?
Abstract (arXiv)
Gradient descent prevails in artificial neural network training, but seems inept for spiking neural networks as small parameter changes can cause sudden, disruptive (dis-)appearances of spikes. Here, we demonstrate exact gradient descent based on continuously changing spiking dynamics. These are generated by neuron models whose spikes vanish and appear at the end of a trial, where it cannot influence subsequent dynamics. This also enables gradient-based spike addition and removal. We illustrate our scheme with various tasks and setups, including recurrent and deep, initially silent networks.
Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). First posted on arXiv 25 Sep 2023.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2023: 1; 2024: 2; 2025: 3; 2026: 4.
10 papers.
- 2024DelGrad: Exact event-based gradients for training delays and weights on spiking neuromorphic hardwarecited by 9
- 2023SparseProp: Efficient Event-Based Simulation and Training of Sparse Recurrent Spiking Neural Networkscited by 6
- 2024Stable Learning Using Spiking Neural Networks Equipped With Affine Encoders and Decoderscited by 5
- 2025Causal pieces: analysing and improving spiking neural networks piece by piececited by 2
- 2026Training event-based neural networks with exact gradients via Differentiable ODE Solving in JAXcited by 2
- 2025A ghost mechanism: An analytical model of abrupt learning in recurrent networkscited by 1
- 2026Equivalence of approximation by networks of single- and multi-spike neuronscited by 1
- 2026Quadratic integrate-and-fire neurons exhibit less fragmented loss landscapes and outperform leaky integrate-and-fire neurons in spike-based gradient descentcited by 1
- 2025Advanced Torrential Loss Function for Precipitation Forecastingcited by 0
- 2026Scalable Training of Continuous-Time Spiking Neural Networks with Differentiable Spike-Time Discretizationcited by 0
- 2026Scalable Training of Continuous-Time Spiking Neural Networks with Differentiable Spike-Time Discretization16 Jul 2026
- 2026Quadratic integrate-and-fire neurons exhibit less fragmented loss landscapes and outperform leaky integrate-and-fire neurons in spike-based gradient descent2 Jun 2026
- 2026Equivalence of approximation by networks of single- and multi-spike neurons13 Mar 2026
- 2026Training event-based neural networks with exact gradients via Differentiable ODE Solving in JAX9 Mar 2026
- 2025Advanced Torrential Loss Function for Precipitation Forecasting1 Sep 2025
- 2025Causal pieces: analysing and improving spiking neural networks piece by piece18 Apr 2025
- 2025A ghost mechanism: An analytical model of abrupt learning in recurrent networks4 Jan 2025
- 2024DelGrad: Exact event-based gradients for training delays and weights on spiking neuromorphic hardware30 Apr 2024
- 2024Stable Learning Using Spiking Neural Networks Equipped With Affine Encoders and Decoders6 Apr 2024
- 2023SparseProp: Efficient Event-Based Simulation and Training of Sparse Recurrent Spiking Neural Networks28 Dec 2023