Deep Learning of Part-based Representation of Data Using Sparse Autoencoders with Nonnegativity Constraints

Autor:	Hosseini-Asl, Ehsan, Zurada, Jacek M., Nasraoui, Olfa
Rok vydání:	2016
Předmět:	Computer Science - Learning Statistics - Machine Learning
Druh dokumentu:	Working Paper
DOI:	10.1109/TNNLS.2015.2479223
Popis:	We demonstrate a new deep learning autoencoder network, trained by a nonnegativity constraint algorithm (NCAE), that learns features which 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 dataset. 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. Comment: Accepted for publication in IEEE Transactions of Neural Networks and Learning Systems
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/1601.02733 Zobrazit plný text záznamu View this record from Arxiv