Developing Fast Machine Learning Algorithm based on Auxiliary Function-based Optimization Approach
| Project/Area Number |
26540090
|
|---|
| Research Category |
Grant-in-Aid for Challenging Exploratory Research
|
| Allocation Type | Multi-year Fund |
|---|
| Research Field |
Perceptual information processing
|
|---|
| Research Institution | National Institute of Informatics |
|---|
Principal Investigator |
ONO Nobutaka 国立情報学研究所, 情報学プリンシプル研究系, 准教授 (80334259)
|
|---|
| Project Period (FY) |
2014-04-01 – 2016-03-31
|
| Project Status |
Completed (Fiscal Year 2015)
|
| Budget Amount *help |
¥3,640,000 (Direct Cost: ¥2,800,000、Indirect Cost: ¥840,000)
Fiscal Year 2015: ¥2,080,000 (Direct Cost: ¥1,600,000、Indirect Cost: ¥480,000)
Fiscal Year 2014: ¥1,560,000 (Direct Cost: ¥1,200,000、Indirect Cost: ¥360,000)
|
|---|
| Keywords | 深層学習 / 補助関数法 / ニューラルネットワーク / 最適化 / パターン認識 / バックプロパゲーション / 補助関数 |
|---|
| Outline of Final Research Achievements |
We derived a quadratic auxiliary function with a look-up table for 2-layer neural network with a tangent hyperbolic activation function. Also, for training multi-layer neural network, we showed the auxiliary function could be designed from the output to the input recursively, and improved the algorithm based on a new concept of “back propagation of target”. By experiments with MIST handwritten digit database, we showed the derived algorithm needed much less iterations for convergence than a conventional adaptive gradient method.
|
Report
(3 results)
Research Products
(3 results)
