Small-sample Deep Learning Method Based on Analytic Initialization of Convolutional Layers
Project/Area Number |
26730085
|
Research Category |
Grant-in-Aid for Young Scientists (B)
|
Allocation Type | Multi-year Fund |
Research Field |
Perceptual information processing
|
Research Institution | The University of Tokyo |
Principal Investigator |
Nakayama Hideki 東京大学, 情報理工学(系)研究科, 講師 (00643305)
|
Project Period (FY) |
2014-04-01 – 2016-03-31
|
Project Status |
Completed (Fiscal Year 2015)
|
Budget Amount *help |
¥3,770,000 (Direct Cost: ¥2,900,000、Indirect Cost: ¥870,000)
Fiscal Year 2015: ¥1,560,000 (Direct Cost: ¥1,200,000、Indirect Cost: ¥360,000)
Fiscal Year 2014: ¥2,210,000 (Direct Cost: ¥1,700,000、Indirect Cost: ¥510,000)
|
Keywords | 深層学習 / ディープラーニング / 画像認識 / 畳み込みニューラルネットワーク / 表現学習 / 人工知能 / 少サンプル学習 |
Outline of Final Research Achievements |
We proposed a new deep learning methodology that enable fast and stable learning from limited amount training examples. We stacked convolutional layers using discriminative analytic solutions obtained by Fisher weight map to build multi-layer convolutional neural networks. Then we further fine tune the entire network by means of the standard backpropagation to quickly reach better local minima. Proposed method achieved state-of-the-art classification accuracy on some standard benchmarks, namely MNIST and STL-10.
|
Report
(3 results)
Research Products
(14 results)
-
-
-
-
-
-
[Presentation] 深層一般化正準相関分析2016
Author(s)
岩瀬智亮,中山英樹
Organizer
情報処理学会第78回全国大会
Place of Presentation
慶應義塾大学矢上キャンパス,神奈川県横浜市
Year and Date
2016-03-10
Related Report
-
-
-
-
-
-
-
-