jaxsnn: Event-driven Gradient Estimation for Analog Neuromorphic Hardware
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_ | 1866910311310688256 |
|---|---|
| author | Müller, Eric Althaus, Moritz Arnold, Elias Spilger, Philipp Pehle, Christian Schemmel, Johannes |
| author_facet | Müller, Eric Althaus, Moritz Arnold, Elias Spilger, Philipp Pehle, Christian Schemmel, Johannes |
| contents | Traditional neuromorphic hardware architectures rely on event-driven computation, where the asynchronous transmission of events, such as spikes, triggers local computations within synapses and neurons. While machine learning frameworks are commonly used for gradient-based training, their emphasis on dense data structures poses challenges for processing asynchronous data such as spike trains. This problem is particularly pronounced for typical tensor data structures. In this context, we present a novel library (jaxsnn) built on top of JAX, that departs from conventional machine learning frameworks by providing flexibility in the data structures used and the handling of time, while maintaining Autograd functionality and composability. Our library facilitates the simulation of spiking neural networks and gradient estimation, with a focus on compatibility with time-continuous neuromorphic backends, such as the BrainScaleS-2 system, during the forward pass. This approach opens avenues for more efficient and flexible training of spiking neural networks, bridging the gap between traditional neuromorphic architectures and contemporary machine learning frameworks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_16841 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | jaxsnn: Event-driven Gradient Estimation for Analog Neuromorphic Hardware Müller, Eric Althaus, Moritz Arnold, Elias Spilger, Philipp Pehle, Christian Schemmel, Johannes Neural and Evolutionary Computing Traditional neuromorphic hardware architectures rely on event-driven computation, where the asynchronous transmission of events, such as spikes, triggers local computations within synapses and neurons. While machine learning frameworks are commonly used for gradient-based training, their emphasis on dense data structures poses challenges for processing asynchronous data such as spike trains. This problem is particularly pronounced for typical tensor data structures. In this context, we present a novel library (jaxsnn) built on top of JAX, that departs from conventional machine learning frameworks by providing flexibility in the data structures used and the handling of time, while maintaining Autograd functionality and composability. Our library facilitates the simulation of spiking neural networks and gradient estimation, with a focus on compatibility with time-continuous neuromorphic backends, such as the BrainScaleS-2 system, during the forward pass. This approach opens avenues for more efficient and flexible training of spiking neural networks, bridging the gap between traditional neuromorphic architectures and contemporary machine learning frameworks. |
| title | jaxsnn: Event-driven Gradient Estimation for Analog Neuromorphic Hardware |
| topic | Neural and Evolutionary Computing |
| url | https://arxiv.org/abs/2401.16841 |