We achieve a new state-of-the-art of $12. 8\%$ WER for visual speech recognition on the TED LRS3 dataset, which rivals the performance of audio-only models from just four years ago.
We propose an MNIST based test as an easy instance of the symbol grounding problem that can serve as a sanity check for differentiable symbolic solvers in general.
Two main obstacles preventing the widespread adoption of variational Bayesian neural networks are the high parameter overhead that makes them infeasible on large networks, and the difficulty of implementation, which can be thought of as "programming overhead."
Linearly interpolating between the latent embeddings for a good agent and a bad agent yields an agent embedding that generates a network with intermediate performance, where the performance can be tuned according to the coefficient of interpolation.
Our model learns a rich latent space of the biological peptide context by taking advantage of abundant, unlabeled peptide sequences.
We also describe a method we call regeneration to train the network without explicit optimization, by injecting the network with predictions of its own parameters.
We also present two novel hash functions, the Dirichlet hash and the Neighborhood hash, and use them to demonstrate experimentally that balanced and deterministic weight-sharing helps with the performance of a neural network.