2009 Fiscal Year Final Research Report
Learning of a sparse code by a constrained optimization
| Project/Area Number |
19700219
|
|---|
| Research Category |
Grant-in-Aid for Young Scientists (B)
|
| Allocation Type | Single-year Grants |
|---|
| Research Field |
Sensitivity informatics/Soft computing
|
|---|
| Research Institution | Kyoto University (2008-2009)
Nara Institute of Science and Technology (2007) |
|---|
Principal Investigator |
SHIN-ICHI Maeda Kyoto University, 情報学研究科, 助教 (20379530)
|
|---|
| Project Period (FY) |
2007 – 2009
|
| Keywords | 階層ニューラルネットワーク / Contrastive Divergence Learning / 制約付き最適化 / EMアルゴリズム |
|---|
| Research Abstract |
Hinton et al. (2006) showed that the performance of hierarchical neural networks couldbe greatly improved by an innovation of the learning algorithm and training with a largeamount of data. In this research project, I aim to clear up the causes which enable anefficient learning. As the results, I've succeeded to clearly show the reason why thelearning by EM algorithm freezes in some cases, generalize contrastive divergencelearning which was used in the training of the hierarchical neural networks and newlyderive the convergence condition of the algorithm. We also successfully demonstrated thatan efficient coding of natural images can be obtained by the learning based on aconstrained optimization.
|
