Sequential Predictive Attention for the Representation of SpiKing Signals

Navigation

Verified details

These details have been verified by PyPI
Maintainers
Avatar for skatchn from gravatar.com skatchn

Unverified details

These details have not been verified by PyPI
Project links
Meta
  • License: GNU GENERAL PUBLIC LICENSE Version 3, 29 June 2007 Copyright (C) 2007 Free Software Foundation, Inc...
  • Author: Nicolas Skatchkovsky
  • Tags Computational neuroscience, Artificial Intelligence, GenAI
  • Requires: Python >=3.9
  • Provides-Extra: scripts
Classifiers

Project description

SPARKS 🎆

This is the official repository for SPARKS: a Sequential Predictive Autoencoder for the Analysis of spiKing Signals.

SPARKS includes a novel self-attention mechanism using Hebbian learning to generate reliable latent representations from single spike timings. SPARKS trains a variational autoencoder with a novel criterion inspired by predictive coding for temporal coherence.

sparks is implemented in PyTorch and includes demos for a quickstart. It can perform supervised or unsupervised to produce low-dimensional latent embeddings which allows to gain biological insights from neural data.

Make sure to 👀 watch or ⭐️ star this repository to keep updated!

Reference

  • 📄 Preprint:

Coming soon!

License

  • SPARKS is an open source software under a GLPv3 license.

Project details

Verified details

These details have been verified by PyPI
Maintainers
Avatar for skatchn from gravatar.com skatchn

Unverified details

These details have not been verified by PyPI
Project links
Meta
  • License: GNU GENERAL PUBLIC LICENSE Version 3, 29 June 2007 Copyright (C) 2007 Free Software Foundation, Inc...
  • Author: Nicolas Skatchkovsky
  • Tags Computational neuroscience, Artificial Intelligence, GenAI
  • Requires: Python >=3.9
  • Provides-Extra: scripts
Classifiers

Release history Release notifications | RSS feed

0.1.1

This version

0.1.0

0.0.1

Download files

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

Source Distribution

sparks_ai-0.1.0.tar.gz (78.8 MB view details)

Uploaded Source

Built Distribution

sparks_ai-0.1.0-py3-none-any.whl (78.6 MB view details)

Uploaded Python 3

File details

Details for the file sparks_ai-0.1.0.tar.gz.

File metadata

  • Download URL: sparks_ai-0.1.0.tar.gz
  • Upload date:
  • Size: 78.8 MB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/5.1.1 CPython/3.10.9

File hashes

Hashes for sparks_ai-0.1.0.tar.gz
Algorithm Hash digest
SHA256 5c76095636e14c6ccdfeea289a82083a99154a8f3bff49b2637cb61cc6be74ed
MD5 d25b7bfb389ae0dee13e93d6d88dfce1
BLAKE2b-256 8ff436359a7d4b2be590fe120de6d00c2b151ef8ace98912619e07e0feacbd89

See more details on using hashes here.

File details

Details for the file sparks_ai-0.1.0-py3-none-any.whl.

File metadata

  • Download URL: sparks_ai-0.1.0-py3-none-any.whl
  • Upload date:
  • Size: 78.6 MB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/5.1.1 CPython/3.10.9

File hashes

Hashes for sparks_ai-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 ef4f3a6e0d7579658c4b5108837337e9757bb10b738e77d24f8537ea8854e4ea
MD5 742070a2853ea738a88b87773a8d4347
BLAKE2b-256 6996131c6069971d8510f94b0fb608e5a4edc9eda8a78497f90b5e6bfade3082

See more details on using hashes here.

Supported by

AWS AWS Cloud computing and Security Sponsor Datadog Datadog Monitoring Fastly Fastly CDN Google Google Download Analytics Microsoft Microsoft PSF Sponsor Pingdom Pingdom Monitoring Sentry Sentry Error logging StatusPage StatusPage Status page