| Presentation | 2002/11/4 Hardware Implementation of Quantized Connection Nonmonotoinc Neural Networks and a Threshold Learning Algorithm Takuya HAGA, Fumihiko ISHIDA, Mitsunaga KINJO, Shigeo SATO, Koji NAKAJIMA, |
|---|---|
| PDF Download Page | PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | To realize high information processing ability of neural networks, implementing an integrated hardware with high speed is essential. To meet these requirements, we adopt two methods. One is weight quantization and another is introduction of nonmonotonic neurons. We consider a network with 3-value {-1,0,+1} weights, which has high capability of integration, but degrade the learning performance. To compensate the degradation, nonmonotonic neurons, which exhibit high learning ability, are introduced. However, the learning performance depends on a threshold which is one of the nonmonotonic neuron's parameter, and the optimum one depends on such as problems and network structures. Therefore, we propose a threshold learning algorithm and confirm the usefulness of the learning algorithm by numerical simulations. Moreover, we have implemented such quantized connection nonmonotonic neural networks with 20 neurons and 400 synapses including the learning module using analog circuits. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Neural Network / Quantized Connection / Nonmonotonic Neuron / Threshold Learning Algorithm / Hardware Implementation |
| Paper # | NC2002-77 |
| Date of Issue |
| Conference Information | |
| Committee | NC |
|---|---|
| Conference Date | 2002/11/4(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) | Hardware Implementation of Quantized Connection Nonmonotoinc Neural Networks and a Threshold Learning Algorithm |
| Sub Title (in English) | |
| Keyword(1) | Neural Network |
| Keyword(2) | Quantized Connection |
| Keyword(3) | Nonmonotonic Neuron |
| Keyword(4) | Threshold Learning Algorithm |
| Keyword(5) | Hardware Implementation |
| 1st Author's Name | Takuya HAGA |
| 1st Author's Affiliation | Research Institute of Electrical Communication, Tohoku University() |
| 2nd Author's Name | Fumihiko ISHIDA |
| 2nd Author's Affiliation | Graduate School of Information Systems, University of Electro-Communications |
| 3rd Author's Name | Mitsunaga KINJO |
| 3rd Author's Affiliation | Research Institute of Electrical Communication, Tohoku University |
| 4th Author's Name | Shigeo SATO |
| 4th Author's Affiliation | Research Institute of Electrical Communication, Tohoku University |
| 5th Author's Name | Koji NAKAJIMA |
| 5th Author's Affiliation | Research Institute of Electrical Communication, Tohoku University |
| Date | 2002/11/4 |
| Paper # | NC2002-77 |
| Volume (vol) | vol.102 |
| Number (no) | 430 |
| Page | pp.pp.- |
| #Pages | 6 |
| Date of Issue | |