Control and Information Processing Functions using Chaotic Dynamics in Neural Network Model and Cellular Automata
| Project/Area Number |
16500131
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (C)
|
| Allocation Type | Single-year Grants |
|---|
| Section | 一般 |
|---|
| Research Field |
Sensitivity informatics/Soft computing
|
|---|
| Research Institution | Okayama University |
|---|
Principal Investigator |
NARA Shigetoshi Okayama University, Graduate School of Science & Technology, Dep. of Elec. & Elec. Eng., Professor (60231495)
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
NAGAYA Tomoyuki Oita University, Faculty of Engineering, Dep. of Elec & Elec. Eng, Professor (00228058)
KUROIWA Jousuke Fukui University, Faculty of Engineering, Dep. Human & Art. Intell. Sys, ASSOCIATE PROFESSOR (10282104)
NISHIKAWA Takeshi Okayama University, Graduate School of Science & Technology, Dep. of Elec & Elec. Eng, Assistant (80243492)
|
|---|
| Project Period (FY) |
2004 – 2006
|
| Project Status |
Completed (Fiscal Year 2006)
|
| Budget Amount *help |
¥3,400,000 (Direct Cost: ¥3,400,000)
Fiscal Year 2006: ¥800,000 (Direct Cost: ¥800,000)
Fiscal Year 2005: ¥1,100,000 (Direct Cost: ¥1,100,000)
Fiscal Year 2004: ¥1,500,000 (Direct Cost: ¥1,500,000)
|
|---|
| Keywords | Neural Network / Chaotic Dynamics / Motion Control / Cellular Automata / Rule Dynamics / Coupled Active Elements / Complete Compressive Description of Video Images / Nonlinear Oscillation |
|---|
| Research Abstract |
It is shown that complex dynamics including chaos can be useful in realizing of complex functions and complex control by means of simple rule (s) . The two computer experiments have been done. One is to use a neural network model and the other is to use cellular automata The former enables us to understand a possible mechanism of memory dynamics in brain and excellent control observed in biological control. The latter enables us not only to analyze complexity contained in sound signal, music and voices, but also to compress data in completely reversible way. Using the neural network model, computer experiment to solve two-dimensional maze which is set as a typical ill-posed problem was done. The performance is evaluated by numerical methods. A plan of hardware implementation is proposed. All works were reported in conference meetings and were submitted to several scientific or engineering journals.
|
Report
(4 results)
Research Products
(37 results)
