Unclaimed brand
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. Here, we fill this gap with a novel method, CEBRA, that jointly uses behavioural and neural data in a hypothesis- or discovery-driven manner to produce consistent, high-performance latent spaces. 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, and rapid, high-accuracy decoding of natural movies from visual cortex.
Liking this brand profile? Share this page
Hex Code
Color name
RGB
HSL
CMYK
#FF0000
Red
255, 0, 0
0, 100, 50
0, 100, 100, 0
#86B7FE
Malibu
134, 183, 254
216, 98, 76
47, 28, 0, 0
#0A53BE
Denim
10, 83, 190
216, 90, 39
95, 56, 0, 25
CEBRA is an innovative brand that specializes in mapping behavioural actions to neural activity, with a focus on neuroscience. They offer a unique machine-learning method that allows for the compression of time series data, revealing hidden structures in the variability of the data. This method is particularly effective for analysing behavioural and neural data recorded simultaneously.
One of the key features of CEBRA is its ability to decode activity from the visual cortex of the mouse brain, reconstructing viewed videos. By leveraging behavioural and neural data in a hypothesis- or discovery-driven manner, CEBRA produces consistent and high-performance latent spaces. It can be used for calcium and electrophysiology datasets, across sensory and motor tasks, and for both simple and complex behaviours across different species.
CEBRA is a valuable tool for researchers in neuroscience, allowing them to uncover neural dynamics and reveal underlying correlates of behavior. It provides a means for hypothesis testing, is compatible with single and multi-session datasets, and can be used label-free. Additionally, CEBRA can be applied to map space, uncover complex kinematic features, and decode natural movies with rapid and high accuracy from the visual cortex.
For further information and access to the CEBRA algorithm, visit their official implementation on GitHub, follow them on Twitter, or subscribe to their mailing list for updates on the project. CEBRA is driving advances in the field of neuroscience and offering exciting possibilities for understanding the connection between behaviour and neural activity
Brand industry
Science and Education
Company type
Suggest company type
Year founded
Suggest founded year
Company size
Suggest company size
