| Project/Area Number |
15300068
|
|---|
| Research Category |
Grant-in-Aid for Scientific Research (B)
|
| Allocation Type | Single-year Grants |
|---|
| Section | 一般 |
|---|
| Research Field |
Sensitivity informatics/Soft computing
|
|---|
| Research Institution | University of Tsukuba |
|---|
Principal Investigator |
MORITA Masahiko University of Tsukuba, Graduate School of Systems and Information Engineering, Associate Professor, 大学院システム情報工学研究科, 助教授 (00222349)
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
SUEMITSU Atsuo Shimane University, Interdisciplinary Faculty of Science and Engineering, Research Associate, 総合理工学部, 教務職員 (20422199)
|
|---|
| Project Period (FY) |
2003 – 2006
|
| Project Status |
Completed (Fiscal Year 2006)
|
| Budget Amount *help |
¥13,100,000 (Direct Cost: ¥13,100,000)
Fiscal Year 2006: ¥2,700,000 (Direct Cost: ¥2,700,000)
Fiscal Year 2005: ¥3,200,000 (Direct Cost: ¥3,200,000)
Fiscal Year 2004: ¥4,400,000 (Direct Cost: ¥4,400,000)
Fiscal Year 2003: ¥2,800,000 (Direct Cost: ¥2,800,000)
|
|---|
| Keywords | trajectory attractor / selective desensitization / nonmonotone neural network / neurodynamical system / pattern-based inference / common sense reasoning / information integration / neural network model / ニューラルネット / 非単調推論 / 分散表現 / 文脈修飾 |
|---|
| Research Abstract |
It is considered that keys to overcome the limitations of classical artificial intelligence are to represent and process distributed information as patterns without symbolizing it, and to apply knowledge learned in a particular context to new situations in various contexts. The present study aimed to develop a pattern-based reasoning system that has high ability of analogical reasoning and common principles to that used in the brain, and obtained the following results.
1. Multilayer neural networks, which are typical pattern-based information processing systems, have difficulty in learning input-output relation that depends strongly on context. To overcome this difficulty, we developed the selective desensitization method, with which part of neural elements are desensitized depending on the context. We show by numerical experiments that this model has much higher learning capacity and generalization performance than the conventional ones. This is because two kinds of distributed representations are integrated without using local representations, which greatly expands the potential of neural networks.
2. By applying the above method to a kind of neural network called a trajectory attractor model, we built a reasoning system using distributed representations alone. This system deduces a conclusion by state transitions along a trajectory attractor formed in a large-scale dynamical system, and has powerful ability of analogical reasoning. We also showed that this system has many advantages over existing reasoning systems, for example, it can make nonmonotonic reasoning in a simple manner.
3. To examine biological plausibility of the principles of our reasoning system, we constructed models of inferotemporal cortex and hippocampus and compare them with neurophysiological data. The results, together with other physiological and psychological grounds, strongly suggested that the selective desensitization method is actually used in the brain.
|
