| Presentation | 2002/3/11 Adaptive Space Reconstruction and Generalization on Hidden Layer in Neural Networks with Local Inputs Katsunari SHIBATA, Koji ITO, |
|---|---|
| PDF Download Page | PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | Our living creatures represent global information in their brain by integrating local sensory signals such as visual sensory signals. In this paper, the state of hidden layer in a. lavered neural network with local inputs after learning was observed for some cases. Some characters became clear as follows. (1)If the training signal changes gradually in space, the hidden layer becomrs to represent the spatial infbrmation. (2)This tendency is stronger in the higher hidden laver. (3)If there are redundant hidden neurons, they represent the global information totally, while each of them keeps the initial fluctuation due to the initial connection weights. (4)If there is no correlation between the training signal of two input region, the learning of one region becomes not to influence to the learning of the other region. (5)However, the hidden neurons does not become to represent the information for only one region. From these results, the reason why the hidden layer becomes to represent spatial information by reinforcement learning [1] can be thought as follows. The state evaluation value changes gradually according to the time to the goal, while motion should change gradually for the states with the same evaluation value. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | layered neural network / localized input / hidden representation / generalization / learning |
| Paper # | NC2001-152 |
| Date of Issue |
| Conference Information | |
| Committee | NC |
|---|---|
| Conference Date | 2002/3/11(1days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | |
| Chair | |
| Vice Chair | |
| Secretary | |
| Assistant | |
| Paper Information | |
| Registration To | Neurocomputing (NC) |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Adaptive Space Reconstruction and Generalization on Hidden Layer in Neural Networks with Local Inputs |
| Sub Title (in English) | |
| Keyword(1) | layered neural network |
| Keyword(2) | localized input |
| Keyword(3) | hidden representation |
| Keyword(4) | generalization |
| Keyword(5) | learning |
| 1st Author's Name | Katsunari SHIBATA |
| 1st Author's Affiliation | Dept. of Electrical & Electronic Engineering. Oita University() |
| 2nd Author's Name | Koji ITO |
| 2nd Author's Affiliation | Dept. of Computational Intelligence and System Science, Tokyo Inst. of Tech. |
| Date | 2002/3/11 |
| Paper # | NC2001-152 |
| Volume (vol) | vol.101 |
| Number (no) | 735 |
| Page | pp.pp.- |
| #Pages | 8 |
| Date of Issue | |