http://scholars.ntou.edu.tw/handle/123456789/4981
標題: | Effects of using different neural network structures and cost functions in locomotion control | 作者: | Jih-Gau Juang | 關鍵字: | UNIVERSAL APPROXIMATION;SIGMOID FUNCTION;WALKING ROBOT | 公開日期: | 2006 | 出版社: | SPRINGER-VERLAG BERLIN | 卷: | 4221 | 起(迄)頁: | 437-446 | 來源出版物: | Advances in Natural Computation, Pt 1 | 摘要: | Effects of using different neural network structures and cost functions in locomotion control are investigated. Simulations focus on refinement and a thorough understanding of an artificial intelligent learning scheme. This scheme uses a neural network controller with backpropagation through time learning rule. Through learning, the controller can generate locomotion trajectory along a pre-defined path. Different issues regarding the scheme have been examined. They include the effects of using different numbers of hidden units, the effects of using only angle parameters in the cost function, and the effects of including an energy criterion in the cost function. |
URI: | http://scholars.ntou.edu.tw/handle/123456789/4981 | ISSN: | 3-540-45901-4 |
顯示於: | 通訊與導航工程學系 |
在 IR 系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。