Event-based backpropagation on the neuromorphic platform SpiNNaker2
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913744219537408 |
|---|---|
| author | Béna, Gabriel Wunderlich, Timo Akl, Mahmoud Vogginger, Bernhard Mayr, Christian Gonzalez, Hector Andres |
| author_facet | Béna, Gabriel Wunderlich, Timo Akl, Mahmoud Vogginger, Bernhard Mayr, Christian Gonzalez, Hector Andres |
| contents | Neuromorphic computing aims to replicate the brain's capabilities for energy efficient and parallel information processing, promising a solution to the increasing demand for faster and more efficient computational systems. Efficient training of neural networks on neuromorphic hardware requires the development of training algorithms that retain the sparsity of spike-based communication during training. Here, we report on the first implementation of event-based backpropagation on the SpiNNaker2 neuromorphic hardware platform. We use EventProp, an algorithm for event-based backpropagation in spiking neural networks (SNNs), to compute exact gradients using sparse communication of error signals between neurons. Our implementation computes multi-layer networks of leaky integrate-and-fire neurons using discretized versions of the differential equations and their adjoints, and uses event packets to transmit spikes and error signals between network layers. We demonstrate a proof-of-concept of batch-parallelized, on-chip training of SNNs using the Yin Yang dataset, and provide an off-chip implementation for efficient prototyping, hyper-parameter search, and hybrid training methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_15021 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Event-based backpropagation on the neuromorphic platform SpiNNaker2 Béna, Gabriel Wunderlich, Timo Akl, Mahmoud Vogginger, Bernhard Mayr, Christian Gonzalez, Hector Andres Neural and Evolutionary Computing Hardware Architecture Emerging Technologies Neuromorphic computing aims to replicate the brain's capabilities for energy efficient and parallel information processing, promising a solution to the increasing demand for faster and more efficient computational systems. Efficient training of neural networks on neuromorphic hardware requires the development of training algorithms that retain the sparsity of spike-based communication during training. Here, we report on the first implementation of event-based backpropagation on the SpiNNaker2 neuromorphic hardware platform. We use EventProp, an algorithm for event-based backpropagation in spiking neural networks (SNNs), to compute exact gradients using sparse communication of error signals between neurons. Our implementation computes multi-layer networks of leaky integrate-and-fire neurons using discretized versions of the differential equations and their adjoints, and uses event packets to transmit spikes and error signals between network layers. We demonstrate a proof-of-concept of batch-parallelized, on-chip training of SNNs using the Yin Yang dataset, and provide an off-chip implementation for efficient prototyping, hyper-parameter search, and hybrid training methods. |
| title | Event-based backpropagation on the neuromorphic platform SpiNNaker2 |
| topic | Neural and Evolutionary Computing Hardware Architecture Emerging Technologies |
| url | https://arxiv.org/abs/2412.15021 |