| Project/Area Number |
25420344
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Multi-year Fund |
|---|
| Section | 一般 |
|---|
| Research Field |
Electron device/Electronic equipment
|
|---|
| Research Institution | Nihon University |
|---|
Principal Investigator |
|
|---|
| Project Period (FY) |
2013-04-01 – 2016-03-31
|
| Project Status |
Completed (Fiscal Year 2015)
|
| Budget Amount *help |
¥5,200,000 (Direct Cost: ¥4,000,000、Indirect Cost: ¥1,200,000)
Fiscal Year 2015: ¥1,560,000 (Direct Cost: ¥1,200,000、Indirect Cost: ¥360,000)
Fiscal Year 2014: ¥1,950,000 (Direct Cost: ¥1,500,000、Indirect Cost: ¥450,000)
Fiscal Year 2013: ¥1,690,000 (Direct Cost: ¥1,300,000、Indirect Cost: ¥390,000)
|
|---|
| Keywords | デバイス / ニューロンモデル / セルラーニューラルネットワーク / ロバスト / 集積回路 / VDEC / 低容量 / 実装 / ＶＤＥＣ / 試作 |
|---|
| Outline of Final Research Achievements |
Recent neural networks studies have been undertaken with the purpose of applying engineering to the brain function. As a method for modeling the information processing function of the brain, the artificial neural network (ANN) has been suggested. Therefore, it is necessary to construct ANN using neuron models. When a large-scale ANN is constructed, it is desired that its neuron models has a small area.
In this research, we propose the constitution of the low value capacitor implementation model. As a result, it is shown that the proposed model is able to achieve oscillation using 1 fF capacitors. Furthermore, we suggest novel model with input unit. As a result, we clarify the proposed neuron model is superior with the robustness. So, we combine the novel model with a synaptic learning model, suggested an ANN that specializes in image recognition and corresponds to high resolution images. As a result, we clarify the proposed ANN is able to recognize various input data.
|
