# Deep Continuous Local Learning (DECOLLE)
DECOLLE is an online learning framework for spiking neural networks. The algorithmic details are described in this [Frontiers paper](https://www.frontiersin.org/articles/10.3389/fnins.2020.00424/full). If you use this work in your research, please cite as:
` @ARTICLE{decolle2020, AUTHOR={Kaiser, Jacques and Mostafa, Hesham and Neftci, Emre}, TITLE={Synaptic Plasticity Dynamics for Deep Continuous Local Learning (DECOLLE)}, JOURNAL={Frontiers in Neuroscience}, VOLUME={14}, PAGES={424}, YEAR={2020}, URL={https://www.frontiersin.org/article/10.3389/fnins.2020.00424}, DOI={10.3389/fnins.2020.00424}, ISSN={1662-453X} `
### Installing Clone and install. The Python setuptools will take care of dependencies ` git clone https://github.com/nmi-lab/decolle-public.git cd decolle-public python setup.py install --user `
The following will run decolle on the default parameter set ` cd scripts python train_lenet_decolle.py `
All parameter sets are contained in scripts/parameters, you can use them as such: ` cd scripts python train_lenet_decolle.py --params_file=parameters/params_dvsgestures_torchneuromorphic_attention.yml `
## Authors
Emre Neftci - Initial work - [eneftci](https://github.com/eneftci)
Jacques Kaiser - [jackokaiser](https://github.com/jackokaiser)
Massi Iacono - [miacono](https://github.com/miacono)
## License
This project is licensed under the GPLv3 License - see the [LICENSE.txt](LICENSE.txt) file for details
1 maintainer
Metadata
1 maintainer
Release files for decolle 0.2
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| decolle-0.2.tar.gz | 38.6 kB | Without provenance | Details for decolle-0.2.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| decolle-0.2-py3-none-any.whl | Python 3 | none | any | Details for decolle-0.2-py3-none-any.whl |
Total release size: 82.2 kB
Release files / decolle-0.2.tar.gz
| Download URL | decolle-0.2.tar.gz |
|---|---|
| Size | 38.6 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
f50b3659d3882be660bcd71037e154b01df3edc71e22f426e21e3d0fd670f8a1
|
|
BLAKE2b-256 checksum How to use checksums |
f94acf5b2ac54b99660f00923047638e2904f84762fc00185c22e00039b27aeb
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/3.6.0 importlib_metadata/4.8.1 pkginfo/1.8.3 requests/2.27.1 requests-toolbelt/0.9.1 tqdm/4.64.0 CPython/3.10.5
|
Release files / decolle-0.2-py3-none-any.whl
| Download URL | decolle-0.2-py3-none-any.whl |
|---|---|
| Size | 43.5 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
16ba50ee5ffe37454fab5894154986f60101954a94e84c6103050c75f282b47f
|
|
BLAKE2b-256 checksum How to use checksums |
adccd7054d262c01f1d86e1350916f5adcf19f3094edc802c5e0e8cea929a551
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/3.6.0 importlib_metadata/4.8.1 pkginfo/1.8.3 requests/2.27.1 requests-toolbelt/0.9.1 tqdm/4.64.0 CPython/3.10.5
|
Security for decolle 0.2
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.
