期刊
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
卷 27, 期 12, 页码 2486-2498出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TNNLS.2015.2479223
关键词
Autoencoder; deep architectures; feature learning; nonnegativity constraints; part-based representation
类别
资金
- Kentucky Science and Engineering Foundation [KSEF-3113-RDE-017]
We demonstrate a new deep learning autoencoder network, trained by a nonnegativity constraint algorithm (nonnegativity-constrained autoencoder), that learns features that show part-based representation of data. The learning algorithm is based on constraining negative weights. The performance of the algorithm is assessed based on decomposing data into parts and its prediction performance is tested on three standard image data sets and one text data set. The results indicate that the nonnegativity constraint forces the autoencoder to learn features that amount to a part-based representation of data, while improving sparsity and reconstruction quality in comparison with the traditional sparse autoencoder and nonnegative matrix factorization. It is also shown that this newly acquired representation improves the prediction performance of a deep neural network.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据