Search Results for author:
Found 10 papers, 1 papers with code
Conformers are All You Need for Visual Speech Recogntion
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.
Assessing SATNet's Ability to Solve the Symbol Grounding Problem
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.
Principled Weight Initialization for Hypernetworks
Hypernetworks are meta neural networks that generate weights for a main neural network in an end-to-end differentiable manner.
Ensemble Model Patching: A Parameter-Efficient Variational Bayesian Neural Network
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."
Seven Myths in Machine Learning Research
We present seven myths commonly believed to be true in machine learning research, circa Feb 2019.
Agent Embeddings: A Latent Representation for Pole-Balancing Networks
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.
PepCVAE: Semi-Supervised Targeted Design of Antimicrobial Peptide Sequences
Our model learns a rich latent space of the biological peptide context by taking advantage of abundant, unlabeled peptide sequences.
Neural Network Quine
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.
Balanced and Deterministic Weight-sharing Helps Network Performance
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.
Gradient Normalization & Depth Based Decay For Deep Learning
In this paper we introduce a novel method of gradient normalization and decay with respect to depth.
