Cebra
Description
CEBRA: A powerful AI tool for neuroscientists to analyze and decode behavioural and neural data. Utilizing non-linear techniques, CEBRA creates consistent latent spaces from joint behavioural and neural data to uncover underlying neural representations. Validated for accuracy on various datasets, it enables hypothesis testing, discovery-driven analysis, and rapid decoding of natural movies from visual cortex. Accessible and label-free, CEBRA is a valuable resource for understanding neural dynamics during adaptive behaviours. Visit GitHub for code and arxiv.org for the pre-print.
About Cebra
Welcome to CEBRA, the cutting-edge machine learning tool that revolutionizes the analysis and decoding of behavioural and neural data in neuroscience research. By harnessing the power of non-linear techniques, CEBRA creates consistent and high-performance latent spaces from joint behavioural and neural data recorded simultaneously.
Our tool enables you to map behavioural actions to neural activity, providing a deeper understanding of neural dynamics during adaptive behaviours. Through this mapping, CEBRA unveils underlying correlates of behaviour, empowering you to unravel the intricate workings of the brain.
CEBRA generates neural latent embeddings that can be utilized for both hypothesis testing and discovery-driven analysis. Our tool has undergone rigorous validation, showcasing exceptional accuracy and efficacy across various datasets including calcium and electrophysiology data. Furthermore, CEBRA proves reliable across sensory and motor tasks, as well as in simple or complex behaviours across different species.
Whether you are working with single or multi-session datasets, CEBRA is your go-to solution. It can be used label-free, providing flexibility and convenience. CEBRA excels at mapping and uncovering complex kinematic features, guaranteeing consistent latent spaces across 2-photon and Neuropixels data. Additionally, our tool offers rapid high-accuracy decoding of natural movies from the visual cortex, enabling groundbreaking insights into the neural representation of visual stimuli.
Excitingly, the code for CEBRA is readily available on GitHub, ensuring both transparency and accessibility. Furthermore, you can access our pre-print on arxiv.org, allowing you to stay up-to-date with the latest findings and advancements.
Are you ready to uncover the hidden secrets of the brain? Join countless neuroscientists who have already benefited from CEBRA's capabilities in analyzing and decoding behavioural and neural data. Start using CEBRA today and gain valuable insights into underlying neural representations.