Presentation | 1996/6/21 Adaptive Multilayer Perceptrons with Automatic Gain Scaling Jianting CAO, Andrzej CICHOCKI, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | In this paper, we present feedforward neural network with an automatic gain amplifier in the output, layer for solving the scaling problem. We also propose an adaptive learning algorithm for updating the gain factor m(t), so the any range of desired output can be achieved without a prior knowledge of unknown nonlinear system. Due to adaptive gain factor, the high estimation accuracy and fast convergence can be obtained. Simulation results are presented to illustrate the effectiveness and performance of the proposed method. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Learning algorithm / automatic scaling / adaptive neural networks |
Paper # | NC96-11 |
Date of Issue |
Conference Information | |
Committee | NC |
---|---|
Conference Date | 1996/6/21(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 | ENG |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Adaptive Multilayer Perceptrons with Automatic Gain Scaling |
Sub Title (in English) | |
Keyword(1) | Learning algorithm |
Keyword(2) | automatic scaling |
Keyword(3) | adaptive neural networks |
1st Author's Name | Jianting CAO |
1st Author's Affiliation | Laboratory for Artificial Brain Systems, FRP, The Institute of Physical and Chemical Research (RIKEN)() |
2nd Author's Name | Andrzej CICHOCKI |
2nd Author's Affiliation | Laboratory for Artificial Brain Systems, FRP, The Institute of Physical and Chemical Research (RIKEN) |
Date | 1996/6/21 |
Paper # | NC96-11 |
Volume (vol) | vol.96 |
Number (no) | 117 |
Page | pp.pp.- |
#Pages | 6 |
Date of Issue |