Deep Imputation of Skeleton Data
In this project, we develop new DL methods for quantitative description of animal movement, more particularly to better understand how normal behaviors are impaired under specific pharmacological treatments using animal models, such as rodents, which can be studied under different medical conditions and in different environments. These methods will lead to better understand how normal behaviors (e.g. walking, balance, orientation in space, very subtle motion changes) are impaired under specific pharmacological treatments. We developed a DL method, DISK (Deep Imputation for Skeleton data), to replace the missing data from movement recordings with great accuracy (https://doi.org/10.1101/2024.05.03.592173).
This project also aims at improving deep learning methods, by comparing, testing and combining different modularities of neural networks, focusing on unsupervised learning, and pushing the understanding of inferred representations. The resulting methods will be applicable to other domains and most importantly can pave the way to detailed quantitative study of human behaviour including its early changes preceding neurodegenerative deterioration of the brain. Decoding behaviour – finding out what it means and predicting it – bears a great potential for improved diagnostics and new therapeutic strategies for neural disorders.
Date:
30/05/2024
