Deep learning methods to uncover neural population dynamics
Brain-machine interfaces for people with paralysis that achieved record-breaking communication performance
“We aim to understand how large populations of neurons in the brain perform computations and represent intention. We use these insights to develop high-performance, robust, and practical assistive devices for people with disabilities and neurological disorders.”
Wimalasena LN, Braun JF, Keshtkaran MR, Alessandro C, Gallego JA, Tresch MC, Miller LE, Pandarinath C. Estimating muscle activation from EMG using deep learning-based dynamical systems models. Journal of Neural Engineering, in press. doi: 10.1088/1741-2552/ac6369. Preprint on BioRxiv: 10.1101/2021.12.01.470827, posted Dec 03, 2021.
Keshtkaran MR*, Sedler AR*, Chowdhury RH**, Tandon R**, Basrai D, Nguyen SL, Sohn H, Jazayeri M, Miller LE, Pandarinath C. A large-scale neural network training framework for generalized estimation of single-trial population dynamics. Nature Methods, in press. Preprint on BioRxiv: 10.1101/2021.01.13.426570, posted Jan 15, 2021.