Ege Altan

This paper transfers brain-computer interface decoders from monkeys to humans, showing that motor-related neural representations are consistent across species and reducing the need for extensive data.

The paper investigates whether low-dimensional neural manifolds in M1 are present during unconstrained natural movements and finds they are, with similar dimensionality to constrained movements.

This paper evaluates dimensionality estimation algorithms for neural recordings, finds linear methods overestimate nonlinear data, and introduces a deep learning denoising algorithm to improve accuracy.