Neuron Model based on Interaction among Synapses on Dendrites
| Project/Area Number |
15K00332
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Multi-year Fund |
|---|
| Section | 一般 |
|---|
| Research Field |
Soft computing
|
|---|
| Research Institution | Kanazawa University |
|---|
Principal Investigator |
TODO YUKI 金沢大学, 電子情報学系, 准教授 (70636927)
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
唐 政 富山大学, 大学院理工学研究部(工学), 教授 (90227299)
|
|---|
| Project Period (FY) |
2015-04-01 – 2018-03-31
|
| Project Status |
Completed (Fiscal Year 2017)
|
| Budget Amount *help |
¥4,550,000 (Direct Cost: ¥3,500,000、Indirect Cost: ¥1,050,000)
Fiscal Year 2017: ¥1,820,000 (Direct Cost: ¥1,400,000、Indirect Cost: ¥420,000)
Fiscal Year 2016: ¥910,000 (Direct Cost: ¥700,000、Indirect Cost: ¥210,000)
Fiscal Year 2015: ¥1,820,000 (Direct Cost: ¥1,400,000、Indirect Cost: ¥420,000)
|
|---|
| Keywords | ニューロン / 樹状突起 / シナプス / 相互作用 / ニューロンコンピューティング / ニューロンモデル / 学習アルゴリズム / バックプロパゲーション学習則 / 遺伝的アルゴリズム / 進化学習アルゴリズム / McCulloch & Pitts モデル / シナプスの相互作用 |
|---|
| Outline of Final Research Achievements |
In this studies, a dendritic neuron model (DNM) based on the nonlinear synapses and their nonlinear interaction among them on dendrites was proposed. Compared with the traditional McCluoch & Pitts model, the proposed dendritic neuron model (DNM) was proved thoeritically and by computer simulations to be capable of solving the linear un-seperatable problems with only one DNM neuron. The proposed dendritic neuron model (DNM) was also be proved mathematically and confirmed by computer simulations to be capable of approximating any comples nonlinear continuous functions.Finally, the proposed dendritic neuron model (DNM)also predicted dendritic structures of several actucal neurons successfully.
|
Report
(4 results)
Research Products
(17 results)
