[BMM 24-25] "Just Relax It": Implementation of different relaxation methods
Implementation of the Gumbel-Sigmoid distribution in PyTorch.
Code for our SIGMORPHON 2023 shared task description paper: Tü-CL at SIGMORPHON 2023: Straight-Through Gradient Estimation for Hard Attention
Code for our SIGMORPHON 2023 shared task description paper: Tü-CL at SIGMORPHON 2023: Straight-Through Gradient Estimation for Hard Attention
Implementation of a straight-through gradient wrapper to allow for discrete latent representations. Provides binary discretizer which maps hidden representations to {0, 1} and a learnable multi-value discretizer, which maps hidden activations to their closest value in a set of given size.
Add a description, image, and links to the straight-through-gradient topic page so that developers can more easily learn about it.
To associate your repository with the straight-through-gradient topic, visit your repo's landing page and select "manage topics."