Presentation | 2001/10/12 Robot Navigation based on Time Delay Neural Networks Tetsuro KOMATSU, Qiangfu ZHAO, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | Multilayer perceptron (MLP) is known as a good tool for robot control.Using MLP alone, however, we cannot get complex and intelligent behavior because a MLP makes decision based only on the current inputs and ignores the history. To avoid this problem, memory based neural network(MBNN) can be used. There are many models for MBNN, say recurrent neural network(RNN) and time-delay neural network(TDNN). In this study, we try to adopt TDNN with each hidden and output node being a finite-duration impulse response(FIR) filter. In this paper, we study the evolutionary learning of TDNN and verify the efficiency of TDNN through simulation. In addition, we point out some problems in using TDNN and propose the solution. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Time-Delay Neural Network / robot navigatio / evolutionary learning |
Paper # | NC2001-60 |
Date of Issue |
Conference Information | |
Committee | NC |
---|---|
Conference Date | 2001/10/12(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) | Robot Navigation based on Time Delay Neural Networks |
Sub Title (in English) | |
Keyword(1) | Time-Delay Neural Network |
Keyword(2) | robot navigatio |
Keyword(3) | evolutionary learning |
1st Author's Name | Tetsuro KOMATSU |
1st Author's Affiliation | University of Aizu Graduate School of Computer Science and Engineering() |
2nd Author's Name | Qiangfu ZHAO |
2nd Author's Affiliation | University of Aizu Graduate School of Computer Science and Engineering |
Date | 2001/10/12 |
Paper # | NC2001-60 |
Volume (vol) | vol.101 |
Number (no) | 365 |
Page | pp.pp.- |
#Pages | 5 |
Date of Issue |