Wearing a mask: Compressed representations of variable-length sequences using recurrent neural tangent kernels

Published in In the proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2021

Recommended citation: Sina Alemohammad, Hossein Babaei, Randall Balestriero, Matt Y. Cheung, Ahmed I. Humayun, Daniel LeJeune, Naiming Liu, Lorenzo Luzi, Jasper Tan, Zichao Wang, and Richard G. Baraniuk. Wearing a mask: Compressed representations of variable-length sequences using recurrent neural tangent kernels. In the proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2021.