Project description

spikingtorch

Training spiking neural networks using Pytorch

About

spikingtorch is a lightweight module for training deep spiking 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.

Status

Spikingtorch is still in development.

Quick install

Through pypi:

pip install spikingtorch

Acknowledgements

Argonne National Laboratory's Laboratory Directed Research and Development program.
Threadwork, U.S. Department of Energy Office of Science, Microelectronics Program.

Publications

A. Yanguas-Gil, Coarse scale representation of spiking neural networks: backpropagation through spikes and application to neuromorphic hardware, arXiv:2007.06176

Copyright and license

spikelearn is distributed under the terms of BSD License. See LICENSE

Project details

These details have not been verified by PyPI

Project links

Homepage

Release history Release notifications | RSS feed

0.1.3

Jun 16, 2024

This version

0.1.1

Jun 10, 2023

0.1.0

Apr 4, 2023

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

spikingtorch-0.1.1.tar.gz (4.6 kB view details)

Uploaded Jun 10, 2023 Source

Built Distribution

spikingtorch-0.1.1-py3-none-any.whl (5.6 kB view details)

Uploaded Jun 10, 2023 Python 3

File details

Details for the file spikingtorch-0.1.1.tar.gz.

File metadata

Download URL: spikingtorch-0.1.1.tar.gz
Upload date: Jun 10, 2023
Size: 4.6 kB
Tags: Source
Uploaded using Trusted Publishing? No
Uploaded via: twine/4.0.2 CPython/3.9.16

File hashes

Hashes for spikingtorch-0.1.1.tar.gz
Algorithm	Hash digest
SHA256	`3b6bb8146dc80f2fbaf0c0946124b4434ff00ddd67a4b238dc58dcabc765bab9`
MD5	`041cf0e6de284424a6c018b85930b261`
BLAKE2b-256	`4a06bb061d6d2dde1b31df6fe40b942142c8222e4f79a2698b4437e28a8ae1e6`

See more details on using hashes here.

File details

Details for the file spikingtorch-0.1.1-py3-none-any.whl.

File metadata

Download URL: spikingtorch-0.1.1-py3-none-any.whl
Upload date: Jun 10, 2023
Size: 5.6 kB
Tags: Python 3
Uploaded using Trusted Publishing? No
Uploaded via: twine/4.0.2 CPython/3.9.16

File hashes

Hashes for spikingtorch-0.1.1-py3-none-any.whl
Algorithm	Hash digest
SHA256	`9cf239dbf65a3f52bd6e59a90ab600ca9415969ef3923bb39e0759714a1ddc11`
MD5	`fd8b845c8bff46c4439276221245c73e`
BLAKE2b-256	`d786ed1a2f45923138f8044e30409a63a520d99d9fe2ca9a081a743f4ae14b0f`