Evolution and learning in differentiable robots

1 code implementation • 23 May 2024 • Luke Strgar, David Matthews, Tyler Hummer, Sam Kriegman

The automatic design of robots has existed for 30 years but has been constricted by serial non-differentiable design evaluations, premature convergence to simple bodies or clumsy behaviors, and a lack of sim2real transfer to physical machines.

Phoneme Segmentation Using Self-Supervised Speech Models

1 code implementation • 2 Nov 2022 • Luke Strgar, David Harwath

We apply transfer learning to the task of phoneme segmentation and demonstrate the utility of representations learned in self-supervised pre-training for the task.

Segmentation Transfer Learning