Despite their ability to represent highly expressive functions, deep learning models trained with SGD seem to find simple, constrained solutions that generalize surprisingly well.
We show that passing input points through a simple Fourier feature mapping enables a multilayer perceptron (MLP) to learn high-frequency functions in low-dimensional problem domains.
By systematically comparing the public ranking with the final ranking, we assess how much participants adapted to the holdout set over the course of a competition.
We consider the problem of smartphone video-based heart rate estimation, which typically relies on measuring the green color intensity of the user's skin.
Medical Physics Image and Video Processing