| Presentation | 2008-03-12 Generation of long-term memory based on multilayer chaotic neural network capable of sequential learning Shingo EMOTO, Hajime ASAMA, Mihoko OTAKE, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | The human memory has various aspects i.e., meta memory, short-term and long-term memory, semantic and episodic memory. Numerous studies have been done for understanding memory function to date. Individual models have been proposed for each phenomenon. Some of them contradict each other or cannot be coexist, based on the different hypotheses or definitions. However, human neural network in the brain which controls memory has one solid structure. Different models should converge with an integrated model. Purpose of this study is to propose such an integrated model which can represent diversity of memories through combining previous knowledge. Our model consists of two-layered chaotic neural networks with different learning constants. The model successfully simulated meta-memory, successive memory, free recall, loss of mid-term memory, long-term memory, episodic memory, and semantic memory. We discuss the relationship between different memories in terms of simulation results and constitutive principle. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | chaotic neural network / episodic memory / successive learning / semantic memory / long-term memory |
| Paper # | NC2007-113 |
| Date of Issue |
| Conference Information | |
| Committee | NC |
|---|---|
| Conference Date | 2008/3/5(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) | Generation of long-term memory based on multilayer chaotic neural network capable of sequential learning |
| Sub Title (in English) | |
| Keyword(1) | chaotic neural network |
| Keyword(2) | episodic memory |
| Keyword(3) | successive learning |
| Keyword(4) | semantic memory |
| Keyword(5) | long-term memory |
| 1st Author's Name | Shingo EMOTO |
| 1st Author's Affiliation | Research into Artifacts, The University of Tokyo() |
| 2nd Author's Name | Hajime ASAMA |
| 2nd Author's Affiliation | Research into Artifacts, The University of Tokyo |
| 3rd Author's Name | Mihoko OTAKE |
| 3rd Author's Affiliation | Research into Artifacts, The University of Tokyo |
| Date | 2008-03-12 |
| Paper # | NC2007-113 |
| Volume (vol) | vol.107 |
| Number (no) | 542 |
| Page | pp.pp.- |
| #Pages | 6 |
| Date of Issue | |