AdaptiveMotorControlLab/CEBRA

Health v2 · maintenance only

Flags: no_license

Adoption not part of the score

1111 stars · 99 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

CEBRA is a Python library for self-supervised learning of consistent latent embeddings from high-dimensional time-series recordings, using auxiliary behavioral variables. It is implemented in PyTorch and primarily targets joint behavioral and neural data analysis, such as decoding behavior from neural activity.

Use cases

• embed neural recordings into low-dimensional latent spaces
• decode behavior from neural activity
• analyze joint behavioral and neural time series
• dimensionality reduction for neuroscience data
• build robust embeddings that resist domain shifts
• cluster high-dimensional time series with auxiliary labels

When to choose

• you need label-informed, self-supervised embeddings of neural or behavioral time series
• you want to decode behavioral variables from neural activity with high accuracy
• you work with calcium imaging, Neuropixels, or spike-train data in Python/PyTorch

When to avoid

• you need a fully stable API - breaking changes occur between versions
• your data is not time-series or lacks auxiliary variables
• you need a non-Python or non-GPU workflow

Facets

library · maturity active

machine-learning data-visualization nlp machine-learning data-science deep-learning python cross-platform self-supervised-learning contrastive-learning dimensionality-reduction time-series latent-embeddings neural-decoding pytorch neuroscience gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="AdaptiveMotorControlLab/CEBRA")