| Budget Amount *help |
¥57,850,000 (Direct Cost: ¥44,500,000、Indirect Cost: ¥13,350,000)
Fiscal Year 2019: ¥11,310,000 (Direct Cost: ¥8,700,000、Indirect Cost: ¥2,610,000)
Fiscal Year 2018: ¥11,050,000 (Direct Cost: ¥8,500,000、Indirect Cost: ¥2,550,000)
Fiscal Year 2017: ¥11,050,000 (Direct Cost: ¥8,500,000、Indirect Cost: ¥2,550,000)
Fiscal Year 2016: ¥11,830,000 (Direct Cost: ¥9,100,000、Indirect Cost: ¥2,730,000)
Fiscal Year 2015: ¥12,610,000 (Direct Cost: ¥9,700,000、Indirect Cost: ¥2,910,000)
|
|---|
| Outline of Final Research Achievements |
We established a data-mining-based approach to discover and utilize the representation of shitsukan information in the human brain. We developed a method to predict deep neural network (DNN) features of an image from the induced brain activity pattern (brain-to-DNN signal translation), and found hierarchical homology between the brain and DNN. We also developed methods for reconstructing the viewed image using DNN features predicted from brain activity, and succeeded in re-creating texture and material images only from the brain activity measured while they were viewed.
|
