Title | ||
---|---|---|
Chinese News Text Classification of the Stacked Denoising Auto Encoder Based on Adaptive Learning Rate and Additional Momentum Item. |
Abstract | ||
---|---|---|
In order to solve the problem of long training time that the Stacked Denoising Auto Encoder (SDAE) has. A kind of new SDAE is proposed which is based on adaptive learning rate and additional momentum term (LMSDAE). Finally, the LMSDAE is tested by Chinese News Text. The experimental results show that compared with the other three algorithms: SDAE, Sparse Denoising Auto Encoder (SPDAE) and Deep Belief Nets (DBN), the LMSDAE algorithm reduced the training times and increased the convergence rate. The accuracy of text classification can reach 87.95%. |
Year | DOI | Venue |
---|---|---|
2018 | 10.1007/978-3-319-92537-0_66 | ADVANCES IN NEURAL NETWORKS - ISNN 2018 |
Keywords | Field | DocType |
Stacked Denoising Auto Encoder,Adaptive learning rate,Additional momentum term,Text classification | Deep belief nets,Pattern recognition,Computer science,Rate of convergence,Momentum,Artificial intelligence,Denoising auto encoder,Adaptive learning rate | Conference |
Volume | ISSN | Citations |
10878 | 0302-9743 | 0 |
PageRank | References | Authors |
0.34 | 1 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Shuang Qiu | 1 | 32 | 7.78 |
Mingyang Jiang | 2 | 0 | 0.68 |
Zhifeng Zhang | 3 | 1 | 1.36 |
Yinan Lu | 4 | 19 | 6.62 |
Zhili Pei | 5 | 58 | 6.64 |