2014 Fiscal Year Final Research Report
Enhanced Generalizability by Structural Model Learning
| Project/Area Number |
25540075
|
|---|
| Research Category |
Grant-in-Aid for Challenging Exploratory Research
|
| Allocation Type | Multi-year Fund |
|---|
| Research Field |
Perceptual information processing
|
|---|
| Research Institution | Waseda University |
|---|
Principal Investigator |
|
|---|
| Project Period (FY) |
2013-04-01 – 2015-03-31
|
| Keywords | コンピュータビジョン |
|---|
| Outline of Final Research Achievements |
In the convolutional neural network (CNN), features with invariance under parallel translation, which is essential in image recognition tasks, can be learned by training the neurons that translate to each other by parallel translation together so that they have the same value. Aiming at similar effect in the case of general transformations, we conducted a theoretical research aimed at the application of the theory that can answer the question on the presence of patterns in raw data by uniformly defining algebraic representation of structures and their semantics in the data space. Also, as an example of application of learning algorithm, we compared algorithms for ground object recognition for Landsat images using CNN and support vector machine (SVM).
|
| Free Research Field |
コンピュータビジョン
|
