English

Node-By-Node Greedy Deep Learning for Interpretable Features

Machine Learning 2016-02-22 v1

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 \emph{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.

Keywords

Cite

@article{arxiv.1602.06183,
  title  = {Node-By-Node Greedy Deep Learning for Interpretable Features},
  author = {Ke Wu and Malik Magdon-Ismail},
  journal= {arXiv preprint arXiv:1602.06183},
  year   = {2016}
}
R2 v1 2026-06-22T12:53:49.555Z