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. |
Year | DOI | Venue |
---|---|---|
2016 | 10.1016/j.neucom.2016.08.059 | Neurocomputing |
Keywords | Field | DocType |
Deep networks,Denoising autoencoder,Interpretability,Discriminativeness | Interpretability,Feature fusion,Search engine,MNIST database,Pattern recognition,Computer science,Artificial intelligence,Denoising autoencoder,Machine learning,Performance improvement | Journal |
Volume | Issue | ISSN |
218 | C | 0925-2312 |
Citations | PageRank | References |
11 | 0.49 | 19 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Gang Ma | 1 | 18 | 3.08 |
Xi Yang | 2 | 11 | 1.85 |
Zhang Bo | 3 | 43 | 7.59 |
Zhongzhi Shi | 4 | 2440 | 238.03 |