Design of Neural Network with Autonomy and its Circuit Implementation
| Project/Area Number |
26540127
|
|---|
| Research Category |
Grant-in-Aid for Challenging Exploratory Research
|
| Allocation Type | Multi-year Fund |
|---|
| Research Field |
Soft computing
|
|---|
| Research Institution | The University of Tokushima |
|---|
Principal Investigator |
Yoko Uwate 徳島大学, 大学院理工学研究部, 准教授 (80582642)
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
西尾 芳文 徳島大学, 大学院理工学研究部, 教授 (80253227)
|
|---|
| Project Period (FY) |
2014-04-01 – 2017-03-31
|
| Project Status |
Completed (Fiscal Year 2016)
|
| Budget Amount *help |
¥3,770,000 (Direct Cost: ¥2,900,000、Indirect Cost: ¥870,000)
Fiscal Year 2016: ¥1,170,000 (Direct Cost: ¥900,000、Indirect Cost: ¥270,000)
Fiscal Year 2015: ¥1,300,000 (Direct Cost: ¥1,000,000、Indirect Cost: ¥300,000)
Fiscal Year 2014: ¥1,300,000 (Direct Cost: ¥1,000,000、Indirect Cost: ¥300,000)
|
|---|
| Keywords | ニューラルネットワーク / 脳情報処理 / 複雑系ネットワーク / 自律性 / 同期現象 |
|---|
| Outline of Final Research Achievements |
In this study, we investigate autonomy when applying new brain information processing function clarified by neuroscience to artificial neural network. Recently, it has been clarified that firing pattern of neuron group shows polygonal structure in cognitive process. Therefore, we investigate the case where the advanced oscillator neuron model is combined with a polygonal shape.
Next, as an approach toward circuit implementation of a neural network, consider a system in which a neuron model is replaced with a one-dimensional map. Furthermore, we implement the circuit of the proposed neural network. By realizing it in a circuit, enormous data can be processed faster and various applications are expected.
|
Report
(4 results)
Research Products
(28 results)
-
[Journal Article] K-Means Algorithm Using Improved Firefly Algorithm2017
Author(s)
Masaki TAKEUCHI, Thomas OTT, Haruna MATSUSHITA, Yoko UWATE and Yoshifumi NISHIO
-
Journal Title
Proceedings of RISP International Workshop on Nonlinear Circuits, Communications and Signal Processing (NCSP'17)
Volume: 1
Pages: 225-228
Related Report
Peer Reviewed / Open Access / Int'l Joint Research / Acknowledgement Compliant
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
[Presentation] Deep Learning for Noisy Back Propagation2016
Author(s)
Kazuki NAGAO, Shinsaburo KITTAKA, Yoko UWATE and Yoshifumi NISHIO
Organizer
IEEE CASS Shanghai and Shikoku Chapters Joint Workshop on Circuits and Systems (SSJW'16)
Place of Presentation
上海交通大学 (上海, 中国)
Year and Date
2016-11-24
Related Report
Int'l Joint Research
-
[Presentation] Features of Firefly Algorithm Inceasing Females2016
Author(s)
Masaki TAKEUCHI, Haruna MATSUSHITA, Yoko UWATE and Yoshifumi NISHIO
Organizer
Taiwan and Japan Conference on Circuits and Systems (TJCAS'16)
Place of Presentation
National Cheng Kung University, Tainan, Taiwan
Year and Date
2016-08-01
Related Report
Int'l Joint Research
-
-
-
[Presentation] Firefly Algorithm Focused on Female Moving Distance2016
Author(s)
Masaki TAKEUCHI, Haruna MATSUSHITA, Yoko UWATE and Yoshifumi NISHIO
Organizer
IEEE CASS Guangzhou and Shikoku Chapters Joint Workshop on Circuits and Systems (GSCAS'16)
Place of Presentation
South China University of Technology, Guangzhou, China
Year and Date
2016-07-15
Related Report
Int'l Joint Research
-
