arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1602.06183cs.LG
收藏

针对可解释特征的逐节点贪婪深度学习

Node-By-Node Greedy Deep Learning for Interpretable Features

Department of Computer Science(计算机科学系)

Ke Wu, Malik Magdon-Ismail

摘要:

多层网络在深度学习的保护伞下重新兴起。目前的深度学习算法训练网络的层顺序,提高算法性能,并提供一些规则化。我们提出了一种新的深度网络训练算法,该算法顺序训练\emph{each node in the network}。我们的算法是数量级更快,在节点级别创建更多的可解释的内部表示,而不是牺牲最终的样本外的性能。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑