| Budget Amount *help |
¥43,680,000 (Direct Cost: ¥33,600,000、Indirect Cost: ¥10,080,000)
Fiscal Year 2022: ¥7,930,000 (Direct Cost: ¥6,100,000、Indirect Cost: ¥1,830,000)
Fiscal Year 2021: ¥7,930,000 (Direct Cost: ¥6,100,000、Indirect Cost: ¥1,830,000)
Fiscal Year 2020: ¥7,930,000 (Direct Cost: ¥6,100,000、Indirect Cost: ¥1,830,000)
Fiscal Year 2019: ¥10,660,000 (Direct Cost: ¥8,200,000、Indirect Cost: ¥2,460,000)
Fiscal Year 2018: ¥9,230,000 (Direct Cost: ¥7,100,000、Indirect Cost: ¥2,130,000)
|
|---|
| Outline of Final Research Achievements |
The most serious problem of deep learning (DL) is that its functionality is a black box. In this research project, we develop an informatics and mathematical framework to elucidate the behavior of DL and a data-driven approach to complement it. As for the mathematical framework, we have shown that the plateau phenomenon originating from singular regions can be reduced or eliminated by using a statistical mechanics formulation. In the data-driven approach, we have achieved some results by comparing the input responses of two CNNs using transfer learning and data expansion, and by analyzing the continuity of representations in the brain cortex as a method to improve prediction performance, especially under the limitation of a small data set.
|
