- Python 98.9%
- Shell 0.5%
- Makefile 0.3%
- Dockerfile 0.3%
| Filename | Latest commit message | Latest commit date |
|---|---|---|
|
Some checks failed
Python package / build (latest, ubuntu-latest, 3.10, latest, 2.12.0) (push) Has been cancelled
Python package / build (latest, ubuntu-latest, 3.10, latest, 2.9.1) (push) Has been cancelled
Python package / build (latest, ubuntu-latest, 3.10, legacy, 2.4.0) (push) Has been cancelled
Python package / build (latest, ubuntu-latest, 3.12, latest, 2.12.0) (push) Has been cancelled
Python package / build (latest, ubuntu-latest, 3.12, latest, 2.9.1) (push) Has been cancelled
Python package / build (latest, ubuntu-latest, 3.12, legacy, 2.6.0) (push) Has been cancelled
Python package / build (latest, ubuntu-latest, 3.13, latest, 2.12.0) (push) Has been cancelled
Python package / build (latest, ubuntu-latest, 3.13, latest, 2.9.1) (push) Has been cancelled
Python package / build (latest, ubuntu-latest, 3.14, latest, 2.12.0) (push) Has been cancelled
Python package / build (latest, ubuntu-latest, 3.14, latest, 2.9.1) (push) Has been cancelled
Python package / build (latest, windows-latest, 3.12, latest, 2.6.0) (push) Has been cancelled
Python package / build (legacy, ubuntu-latest, 3.12, latest, 2.6.0) (push) Has been cancelled
Build docs / build (push) Has been cancelled
Python package (latest) / build (push) Has been cancelled
* Update download urls from figshare to s3 bucket * minimize the diff * unify the dataset download funcs * fix accedentally skipped save/load test * include a numpy legacy test * fix windows compatibility for tempfile * fix added test * Fix legacy loading logic * minimize diff in tests * Fix _assert_equal check * Bump version to 0.6.1 * fix loading logic for legacy torch * allowlist float32d * bump python and torch in workflows * add torch 2.6.0 as legacy only * fix codespell typo |
||
| .github | ||
| cebra | ||
| conda | ||
| docs | ||
| tests | ||
| third_party | ||
| tools | ||
| .clabot | ||
| .dockerignore | ||
| .gitignore | ||
| .pre-commit-config.yaml | ||
| .yapfignore | ||
| AUTHORS.md | ||
| CHANGELOG.md | ||
| CITATION.cff | ||
| CLA.md | ||
| CODE_OF_CONDUCT.md | ||
| conftest.py | ||
| Dockerfile | ||
| LICENSE.md | ||
| Makefile | ||
| MANIFEST.in | ||
| NOTICE.yml | ||
| PKGBUILD | ||
| pyproject.toml | ||
| README.md | ||
| reinstall.sh | ||
| setup.cfg | ||
Welcome! 👋
CEBRA is a library for estimating Consistent EmBeddings of high-dimensional Recordings using Auxiliary variables. It contains self-supervised learning algorithms implemented in PyTorch, and has support for a variety of different datasets common in biology and neuroscience.
To receive updates on code releases, please 👀 watch or ⭐️ star this repository!
cebra is a patented self-supervised method for non-linear clustering that allows for label-informed time series analysis.
It can jointly use behavioral and neural data in a hypothesis- or discovery-driven manner to produce consistent, high-performance latent spaces. While it is not specific to neural and behavioral data, this is the first domain we used the tool in. This application case is to obtain a consistent representation of latent variables driving activity and behavior, improving decoding accuracy of behavioral variables over standard supervised learning, and obtaining embeddings which are robust to domain shifts.
References
-
📄 Publication April 2025: Time-series attribution maps with regularized contrastive learning. Steffen Schneider, Rodrigo González Laiz, Anastasiia Filipova, Markus Frey, Mackenzie Weygandt Mathis. AISTATS 2025.
-
📄 Publication May 2023: Learnable latent embeddings for joint behavioural and neural analysis. Steffen Schneider*, Jin Hwa Lee* and Mackenzie Weygandt Mathis. Nature 2023.
-
📄 Preprint April 2022: Learnable latent embeddings for joint behavioral and neural analysis. Steffen Schneider*, Jin Hwa Lee* and Mackenzie Weygandt Mathis
Patent Information
- Dimensionality reduction of time-series data, and systems and devices that use the resultant embeddings. Steffen Schneider* & Mackenzie Weygandt Mathis*. Awarded Dec 2025. Please contact the TTO office at EPFL for licensing.
License
- Since version 0.4.0, CEBRA is open source software under an Apache 2.0 license.
- Prior versions 0.1.0 to 0.3.1 were released for academic use only (please read the license file).