Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2511.11320 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914158533935104 |
|---|---|
| author | Lin, Jiaqi Jiang, Yi Sengupta, Abhronil |
| author_facet | Lin, Jiaqi Jiang, Yi Sengupta, Abhronil |
| contents | Spiking Neural Networks (SNNs) promise energy-efficient, sparse, biologically inspired computation. Training them with Backpropagation Through Time (BPTT) and surrogate gradients achieves strong performance but remains biologically implausible. Equilibrium Propagation (EP) provides a more local and biologically grounded alternative. However, existing EP frameworks, primarily based on deterministic neurons, either require complex mechanisms to handle discontinuities in spiking dynamics or fail to scale beyond simple visual tasks. Inspired by the stochastic nature of biological spiking mechanism and recent hardware trends, we propose a stochastic EP framework that integrates probabilistic spiking neurons into the EP paradigm. This formulation smoothens the optimization landscape, stabilizes training, and enables scalable learning in deep convolutional spiking convergent recurrent neural networks (CRNNs). We provide theoretical guarantees showing that the proposed stochastic EP dynamics approximate deterministic EP under mean-field theory, thereby inheriting its underlying theoretical guarantees. The proposed framework narrows the gap to both BPTT-trained SNNs and EP-trained non-spiking CRNNs in vision benchmarks while preserving locality, highlighting stochastic EP as a promising direction for neuromorphic and on-chip learning. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_11320 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | StochEP: Stochastic Equilibrium Propagation for Spiking Convergent Recurrent Neural Networks Lin, Jiaqi Jiang, Yi Sengupta, Abhronil Emerging Technologies Machine Learning Spiking Neural Networks (SNNs) promise energy-efficient, sparse, biologically inspired computation. Training them with Backpropagation Through Time (BPTT) and surrogate gradients achieves strong performance but remains biologically implausible. Equilibrium Propagation (EP) provides a more local and biologically grounded alternative. However, existing EP frameworks, primarily based on deterministic neurons, either require complex mechanisms to handle discontinuities in spiking dynamics or fail to scale beyond simple visual tasks. Inspired by the stochastic nature of biological spiking mechanism and recent hardware trends, we propose a stochastic EP framework that integrates probabilistic spiking neurons into the EP paradigm. This formulation smoothens the optimization landscape, stabilizes training, and enables scalable learning in deep convolutional spiking convergent recurrent neural networks (CRNNs). We provide theoretical guarantees showing that the proposed stochastic EP dynamics approximate deterministic EP under mean-field theory, thereby inheriting its underlying theoretical guarantees. The proposed framework narrows the gap to both BPTT-trained SNNs and EP-trained non-spiking CRNNs in vision benchmarks while preserving locality, highlighting stochastic EP as a promising direction for neuromorphic and on-chip learning. |
| title | StochEP: Stochastic Equilibrium Propagation for Spiking Convergent Recurrent Neural Networks |
| topic | Emerging Technologies Machine Learning |
| url | https://arxiv.org/abs/2511.11320 |