# spikingtorch
Training spiking neural networks using Pytorch
## About
`spikingtorch` is a lightweight package for training deep neural
networks using Pytorch. `spikingtorch` includes encoders that transform
standard ML datasets into spike trains, and decoders that transform
the output spikes into values that can be used with loss functions in
Pytorch.
`spikingtorch` implements spiking neural networks and backpropagation
through spikes for [leaky integrate and fire](https://en.wikipedia.org/wiki/Biological_neuron_model#Leaky_integrate-and-fire) neurons.
In addition to the Python package, this repository also
implements the methodology
and reproduces the results presented in the paper:
[A. Yanguas-Gil, Coarse scale representation of spiking neural networks:
backpropagation through spikes and application to neuromorphic
hardware, arXiv:2007.06176](https://arxiv.org/abs/2007.06176)
## Status
`spikingtorch` is in active development, with more neuron models coming up
soon.
## Quick install
Through pypi:
```
pip install spikingtorch
```
## Acknowledgements
* Threadwork, U.S. Department of Energy Office of Science,
Microelectronics Program.
The original implementation was based on reseach funded through Argonne's Laboratory Directed Research
and Development program.
## Publications
Spikingtorch's backpropagation approach is based on the following work:
[A. Yanguas-Gil, Coarse scale representation of spiking neural networks:
backpropagation through spikes and application to neuromorphic
hardware, arXiv:2007.06176](https://arxiv.org/abs/2007.06176)
## Copyright and license
Copyright © 2023, UChicago Argonne, LLC
spikingtorch is distributed under the terms of BSD License. See
[LICENSE](https://github.com/anglyan/spikingtorch/blob/master/LICENSE.md)
Raw data
{
"_id": null,
"home_page": null,
"name": "spikingtorch",
"maintainer": null,
"docs_url": null,
"requires_python": null,
"maintainer_email": null,
"keywords": "spiking neurons, neural networks, AI, Pytorch, neuromorphic computing, spiking neural networks, neuroscience",
"author": "Angel Yanguas-Gil",
"author_email": null,
"download_url": "https://files.pythonhosted.org/packages/e5/f3/89d16204c4a4c8448636800ce1af01cc9ea8e9f65315a94c1cb7348aeec3/spikingtorch-0.1.3.tar.gz",
"platform": null,
"description": "# spikingtorch\n\nTraining spiking neural networks using Pytorch\n\n## About\n\n`spikingtorch` is a lightweight package for training deep neural\nnetworks using Pytorch. `spikingtorch` includes encoders that transform\nstandard ML datasets into spike trains, and decoders that transform\nthe output spikes into values that can be used with loss functions in\nPytorch.\n\n`spikingtorch` implements spiking neural networks and backpropagation\nthrough spikes for [leaky integrate and fire](https://en.wikipedia.org/wiki/Biological_neuron_model#Leaky_integrate-and-fire) neurons.\n\nIn addition to the Python package, this repository also\n implements the methodology\nand reproduces the results presented in the paper:\n\n[A. Yanguas-Gil, Coarse scale representation of spiking neural networks:\nbackpropagation through spikes and application to neuromorphic\nhardware, arXiv:2007.06176](https://arxiv.org/abs/2007.06176)\n\n## Status\n\n`spikingtorch` is in active development, with more neuron models coming up\nsoon.\n\n## Quick install\n\nThrough pypi:\n\n```\npip install spikingtorch\n```\n\n## Acknowledgements\n\n* Threadwork, U.S. Department of Energy Office of Science, \n Microelectronics Program.\n\nThe original implementation was based on reseach funded through Argonne's Laboratory Directed Research\nand Development program.\n\n## Publications\n\nSpikingtorch's backpropagation approach is based on the following work:\n\n[A. Yanguas-Gil, Coarse scale representation of spiking neural networks:\nbackpropagation through spikes and application to neuromorphic\nhardware, arXiv:2007.06176](https://arxiv.org/abs/2007.06176)\n\n\n## Copyright and license\n\nCopyright \u00a9 2023, UChicago Argonne, LLC\n\nspikingtorch is distributed under the terms of BSD License. See \n[LICENSE](https://github.com/anglyan/spikingtorch/blob/master/LICENSE.md)\n\n",
"bugtrack_url": null,
"license": null,
"summary": "Inference and backprop training of spiking neural networks in Pytorch",
"version": "0.1.3",
"project_urls": {
"Homepage": "https://github.com/anglyan/spikingtorch"
},
"split_keywords": [
"spiking neurons",
" neural networks",
" ai",
" pytorch",
" neuromorphic computing",
" spiking neural networks",
" neuroscience"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "948b843a124d96df3a7207b07a29ccf4b9bfe6b8b978722d226ddcd2d3c3e2c6",
"md5": "b9ec0c699aeaf55a39e18cfad836e900",
"sha256": "b4728a6de4361cd8d14a13912efd3c0500553d82ad66e4a53e4e2e837858e1e4"
},
"downloads": -1,
"filename": "spikingtorch-0.1.3-py3-none-any.whl",
"has_sig": false,
"md5_digest": "b9ec0c699aeaf55a39e18cfad836e900",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": null,
"size": 6831,
"upload_time": "2024-06-16T02:54:14",
"upload_time_iso_8601": "2024-06-16T02:54:14.192362Z",
"url": "https://files.pythonhosted.org/packages/94/8b/843a124d96df3a7207b07a29ccf4b9bfe6b8b978722d226ddcd2d3c3e2c6/spikingtorch-0.1.3-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "e5f389d16204c4a4c8448636800ce1af01cc9ea8e9f65315a94c1cb7348aeec3",
"md5": "b9c10fd1e7e76ad94e9ae32793732eb7",
"sha256": "a19f573506cc68815911d5423b56f780f5fc8c9c73fac13880173ca1da5d519e"
},
"downloads": -1,
"filename": "spikingtorch-0.1.3.tar.gz",
"has_sig": false,
"md5_digest": "b9c10fd1e7e76ad94e9ae32793732eb7",
"packagetype": "sdist",
"python_version": "source",
"requires_python": null,
"size": 5909,
"upload_time": "2024-06-16T02:54:15",
"upload_time_iso_8601": "2024-06-16T02:54:15.699718Z",
"url": "https://files.pythonhosted.org/packages/e5/f3/89d16204c4a4c8448636800ce1af01cc9ea8e9f65315a94c1cb7348aeec3/spikingtorch-0.1.3.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-06-16 02:54:15",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "anglyan",
"github_project": "spikingtorch",
"travis_ci": false,
"coveralls": false,
"github_actions": false,
"requirements": [
{
"name": "torch",
"specs": [
[
">=",
"2.0"
]
]
},
{
"name": "torchvision",
"specs": []
},
{
"name": "numpy",
"specs": []
}
],
"lcname": "spikingtorch"
}
JSON
