Cebra

CEBRA: a self-supervised learning algorithm for obtaining interpretable, Consistent EmBeddings of high-dimensional Recordings using Auxiliary variables Nature 2023 Paper Documentation & Demos Code CEBRA is a machine-learning method that can be used to compress time series in a way that reveals otherwise hidden structures in the variability of the data. It excels on behavioural and neural data recorded simultaneously. We have shown it can be used to decode the activity from the visual cortex of the mouse brain to reconstruct a viewed video, to decode trajectories from the sensoirmotor cortex of primates, and for decoding position during navigation. For these use cases and other demos see our Documentation. Demo Applications Video file not supported in this web browser. Application of CEBRA-Behavior to rat hippocampus data (Grosmark and Buzsáki, 2016), showing position/neural activity (left), overlayed with decoding obtained by CEBRA. The current point in embedding space is highlighted (right). CEBRA obtains a median absolute error of 5cm (total track length: 160cm; see Schneider et al. 2023 for details). Video is played at 2x real-time speed. Interactive visualization of the CEBRA embedding for the rat hippocampus data. This 3D plot shows how neural activity is mapped to a lower-dimensional space that correlates with the animal's position and movement direction. Open In Colaboratory Video file not supported in this web browser. CEBRA applied to mouse primary visual cortex, collected at the Allen Institute (de Vries et al. 2020, Siegle et al. 2021). 2-photon and Neuropixels recordings are embedded with CEBRA using DINO frame features as labels. The embedding is used to decode the video frames using a kNN decoder on the CEBRA-Behavior embedding from the test set. Video file not supported in this web browser. CEBRA applied to M1 and S1 neural data, demonstrating how neural activity from primary motor and somatosensory cortices can be effectively embedded and analyzed. See DeWolf et al. 2024 for details. Publications Learnable latent embeddings for joint behavioural and neural analysis Steffen Schneider*, Jin Hwa Lee*, Mackenzie Weygandt Mathis. Nature 2023 A comprehensive introduction to CEBRA, demonstrating its capabilities in joint behavioral and neural analysis across various datasets and species. Read Paper Preprint Time-series attribution maps with regularized contrastive learning Steffen Schneider, Rodrigo González Laiz, Anastasiia Filipova, Markus Frey, Mackenzie Weygandt Mathis. AISTATS 2025 An extension of CEBRA that provides attribution maps for time-series data using regularized contrastive learning. Read Paper Preprint NeurIPS-W 2023 Version Patent Information Patent Pending Please note EPFL has filed a patent titled "Dimensionality reduction of time-series data, and systems and devices that use the resultant embeddings" so if this does not work for your non-academic use case, please contact the Tech Transfer Office at EPFL. Overview Mapping behavioural actions to neural activity is a fundamental goal of neuroscience. As our ability to record large neural and behavioural data increases, there is growing interest in modeling neural dynamics during adaptive behaviors to probe neural representations. In particular, neural latent embeddings can reveal underlying correlates of behavior, yet, we lack non-linear techniques that can explicitly and flexibly leverage joint behavior and neural data to uncover neural dynamics. Here, we fill this gap with a novel encoding method, CEBRA, that jointly uses behavioural and neural data in a (supervised) hypothesis- or (self-supervised) discovery-driven manner to produce both consistent and high-performance latent spaces. We show that consistency can be used as a metric for uncovering meaningful differences, and the inferred latents can be used for decoding. We validate its accuracy and demonstrate our tool's utility for both calcium and electrophysiology datasets, across sensory and motor tasks, and in simple or complex behaviors across species. It allows for single and multi-session datasets to be leveraged for hypothesis testing or can be used label-free. Lastly, we show that CEBRA can be used for the mapping of space, uncovering complex kinematic features, produces consistent latent spaces across 2-photon and Neuropixels data, and can provide rapid, high-accuracy decoding of natural movies from visual cortex. Software You can find our official implementation of the CEBRA algorithm on GitHub: Watch and Star the repository to be notified of future updates and releases. You can also follow us on Twitter for updates on the project. If you are interested in collaborations, please contact us via email. BibTeX Please cite our papers as follows: @article{schneider2023cebra, author={Steffen Schneider and Jin Hwa Lee and Mackenzie Weygandt Mathis}, title={Learnable latent embeddings for joint behavioural and neural analysis}, journal={Nature}, year={2023}, month={May}, day={03}, issn={1476-4687}, doi={10.1038/s41586-023-06031-6}, url={https://doi.org/10.1038/s41586-023-06031-6} } @inproceedings{schneider2025timeseries, title={Time-series attribution maps with regularized contrastive learning}, author={Steffen Schneider and Rodrigo Gonz{\'a}lez Laiz and Anastasiia Filippova and Markus Frey and Mackenzie Weygandt Mathis}, booktitle={The 28th International Conference on Artificial Intelligence and Statistics}, year={2025}, url={https://proceedings.mlr.press/v258/schneider25a.html} } Impact & Citations CEBRA has been cited in numerous high-impact publications across neuroscience, machine learning, and related fields. Our work has influenced research in neural decoding, brain-computer interfaces, computational neuroscience, and machine learning methods for time-series analysis. View All Citations on Google Scholar Our research has been cited in proceedings and journals including Nature Science ICML Nature Neuroscience ICML Neuron NeurIPS ICLR and others. © 2021 - present | EPFL Mathis Laboratory Webpage designed using Bootstrap 5 and Fontawesome 5. --- Skip to main content Back to top Ctrl+K Github Twitter PyPI How to cite CEBRA Ctrl+K On this page Welcome to CEBRA’s documentation!# 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. Please support the development of CEBRA by starring and/or watching the project on Github! Note CEBRA is under active development and the API might include breaking changes between versions. If you use CEBRA in your work, we recommend to double check your current version. For writing reproducible analysis and experiment code, we recommend to use Docker. Installation and Setup# Please see the dedicated Installation Guide for information on installation options using conda, pip and docker. Have fun! 😁 Usage# Please head over to the Usage tab to find step-by-step instructions to use CEBRA on your data. For example use cases, see the Demos tab. Licensing# The ideas presented in our package are patented (Patent US12499131B2). Since version 0.4.0, CEBRA’s source is licenced under an Apache 2.0 license. Prior versions 0.1.0 to 0.3.1 were released for academic use only. Please see the full license file on Github for further information. Contributing# Please refer to the Contributing tab to find our guidelines on contributions. Code Contributors# The CEBRA code was originally developed by Steffen Schneider, Jin H. Lee, and Mackenzie Mathis (up to internal version 0.0.2). Please see our AUTHORS file for more information. Integrations# CEBRA can be directly integrated with existing libraries commonly used in data analysis. Namely, we provide a scikit-learn style interface to use CEBRA. Additionally, we offer integrations with our scikit-learn-style of using CEBRA, a package making use of matplotlib and plotly to plot the CEBRA model results, as well as the possibility to compute CEBRA embeddings on DeepLabCut outputs directly. If you have another suggestion, please head over to Discussions on GitHub! Key References# @article{schneider2023cebra, author = {Schneider, Steffen and Lee, Jin H and Mathis, Mackenzie W}, title = {Learnable latent embeddings for joint behavioural and neural analysis}, journal = {Nature}, doi = {https://doi.org/10.1038/s41586-023-06031-6}, year = {2023}, } @article{xCEBRA2025, author={Steffen Schneider and Rodrigo Gonz{\'a}lez Laiz and Anastasiia Filippova and Markus Frey and Mackenzie W Mathis}, title = {Time-series attribution maps with regularized contrastive learning}, journal = {AISTATS}, url = {https://openreview.net/forum?id=aGrCXoTB4P}, year = {2025}, } This documentation is based on the PyData Theme.