Learnable latent embeddings for joint behavioral and neural analysis
This addresses the need for non-linear techniques in neuroscience to probe neural representations during adaptive behaviors, though it appears incremental as an improvement over existing latent embedding methods.
The authors tackled the problem of mapping behavioral actions to neural activity by developing CEBRA, a novel method that jointly uses behavioral and neural data to produce consistent, high-performance latent embeddings, validated across various datasets and tasks with high-accuracy decoding results.
Mapping behavioral actions to neural activity is a fundamental goal of neuroscience. As our ability to record large neural and behavioral 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 behavioral 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.