Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
4948147 | Neurocomputing | 2016 | 22 Pages |
Abstract
In this paper, we propose a novel deep networks, multi-feature fusion deep networks (MFFDN), based on denoising autoencoder. MFFDN significantly reduces the classification error while giving the interpretability of the hidden-layer feature representation in learning process. Comparing with the traditional denoising autoencoder, MFFDN mainly shows the following advantages: (1) minimally retaining a certain amount of “information” constrained to a given form about its input; (2) explicitly interpreting the meaning of the feature representation in one hidden layer; (3) enhancing discriminativeness of the whole networks. At last, the experiments analysis on MNIST, CIFAR-10 and SVHN prove the state-of-the-art performance improvement of MFFDN with the advantages minimally retaining “information” constraint and the interpreted hidden feature representation.
Related Topics
Physical Sciences and Engineering
Computer Science
Artificial Intelligence
Authors
Gang Ma, Xi Yang, Bo Zhang, Zhongzhi Shi,