Including STDP to eligibility propagation in multi-layer recurrent spiking neural networks
Not on the map. Why?
Abstract (arXiv)
Spiking neural networks (SNNs) in neuromorphic systems are more energy efficient compared to deep learning-based methods, but there is no clear competitive learning algorithm for training such SNNs. Eligibility propagation (e-prop) offers an efficient and biologically plausible way to train competitive recurrent SNNs in low-power neuromorphic hardware. In this report, previous performance of e-prop on a speech classification task is reproduced, and the effects of including STDP-like behavior are analyzed. Including STDP to the ALIF neuron model improves the classification performance, but this is not the case for the Izhikevich e-prop neuron. Finally, it was found that e-prop implemented in a single-layer recurrent SNN consistently outperforms a multi-layer variant.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 27 of its 150 references that are in the map. First posted on arXiv 5 Jan 2022.
Builds on
27 of 150 references.
References · 27
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2014Adam: A Method for Stochastic Optimizationcited by 36,960
- 2014Deep Learning in Neural Networks: An Overviewcited by 765
- 2019On the Variance of the Adaptive Learning Rate and Beyondcited by 763
- 2013Speech Recognition with Deep Recurrent Neural Networkscited by 666
- 2016Target-driven Visual Navigation in Indoor Scenes using Deep Reinforcement Learningcited by 351
- 2016Direct Feedback Alignment Provides Learning in Deep Neural Networkscited by 240
- 2016Training Deep Spiking Neural Networks using Backpropagationcited by 203
- 2018Long short-term memory and learning-to-learn in networks of spiking neuronscited by 179
- 2017SuperSpike: Supervised learning in multi-layer spiking neural networkscited by 178
- 2018Dendritic cortical microcircuits approximate the backpropagation algorithmcited by 96
- 2017A Survey of Neuromorphic Computing and Neural Networks in Hardwarecited by 82
15 more
- 2016Convolutional Networks for Fast, Energy-Efficient Neuromorphic Computingcited by 68
- 2018Eligibility Traces and Plasticity on Behavioral Time Scales: Experimental Support of neoHebbian Three-Factor Learning Rulescited by 64
- 2017Gradient Descent for Spiking Neural Networkscited by 47
- 2019Spiking Neural Networks and Online Learning: An Overview and Perspectivescited by 41
- 2016Neuromorphic Deep Learning Machinescited by 38
- 2020Brain-Inspired Learning on Neuromorphic Substratescited by 35
- 2020Reinforcement co-Learning of Deep and Spiking Neural Networks for Energy-Efficient Mapless Navigation with Neuromorphic Hardwarecited by 32
- 2019Low-Power Neuromorphic Hardware for Signal Processing Applicationscited by 20
- 2019Biologically inspired alternatives to backpropagation through time for learning in recurrent neural netscited by 20
- 2019Spiking Neural Network on Neuromorphic Hardware for Energy-Efficient Unidimensional SLAMcited by 19
- 2018The unreasonable effectiveness of small neural ensembles in high-dimensional braincited by 10
- 2018Short-term Memory of Deep RNNcited by 5
- 2017Bio-Inspired Multi-Layer Spiking Neural Network Extracts Discriminative Features from Speech Signalscited by 4
- 2020Learning Precise Spike Timings with Eligibility Tracescited by 2
- 2016Stochastic single flux quantum neuromorphic computing using magnetically tunable Josephson junctionscited by 1
Built on by
Citing papers per year: 2024: 1.
1 paper.