Node-By-Node Greedy Deep Learning for Interpretable Features

Abstract

Multilayer networks have seen a resurgence under the umbrella of deep learning. Current deep learning algorithms train the layers of the network sequentially, improving algorithmic performance as well as providing some regularization. We present a new training algorithm for deep networks which trains each node in the network sequentially. Our algorithm is orders of magnitude faster, creates more interpretable internal representations at the node level, while not sacrificing on the ultimate out-of-sample performance.

Tasks

Reproductions