# AdaptiveMotorControlLab/CEBRA

Learnable latent embeddings for joint behavioral and neural analysis - Official implementation of CEBRA

Repository: https://github.com/AdaptiveMotorControlLab/CEBRA
Canonical: https://ross.abutalabs.com/products/cebra
Homepage: https://cebra.ai
Language: Python
License: NOASSERTION
License Family: other
Topics: machine-learning, pytorch, contrastive-learning, neuroscience-methods
Last push: 2026-06-28T18:24:12+00:00

## Health v2 (maintenance only)
Score: 86/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 89, release rhythm 74, longevity 100
- inputs: {"age_days": 1612, "days_push": 66, "days_rel": 95, "gap_med": 73, "n_releases_24m": 6}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1111, forks 99 (observed 2026-08-28T04:03:37.605025+00:00)

## What it is
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
- artifact type: library
- maturity: active
- function: machine-learning, data-visualization, nlp
- domain: machine-learning, data-science, deep-learning
- platform: python, cross-platform
- tags: self-supervised-learning, contrastive-learning, dimensionality-reduction, time-series, latent-embeddings, neural-decoding, pytorch, neuroscience, gpu

## Member repositories
- AdaptiveMotorControlLab/CEBRA (main) score 86

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:37.605025+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:42:54.020709+00:00, confidence not recorded.
  - readme: https://github.com/AdaptiveMotorControlLab/CEBRA (fetched 2026-08-28T04:03:37.605025+00:00, sha 667aaa99af37)
  - homepage: https://cebra.ai (fetched 2026-08-29T12:46:54.689006+00:00, sha 5aef1c363b2c)
  - site_page: https://cebra.ai/docs (fetched 2026-08-29T12:46:54.691482+00:00, sha d4f4a6825164)
  - registry_pypi: https://pypi.org/pypi/cebra/json (fetched 2026-08-29T12:46:54.693165+00:00, sha 631ec5563f34)
- Data as of 2026-08-30T08:39:29.467469+00:00.