TY - GEN
T1 - Design of an iterative learning controller of nonlinear dynamic systems with time-varying
AU - Ryu, In Ho
AU - Oh, Hun
AU - Cho, Hyun Seob
PY - 2011
Y1 - 2011
N2 - Connectionist networks, also called neural networks, have been broadly applied to solve many different problems since McCulloch and Pitts had shown mathematically their information processing ability in 1943. In this thesis, we present a genetic neuro-control scheme for nonlinear systems. Our method is different from those using supervised learning algorithms, such as the backpropagation (BP) algorithm, that needs training information in each step. The contributions of this thesis are the new approach to constructing neural network architecture and its training.
AB - Connectionist networks, also called neural networks, have been broadly applied to solve many different problems since McCulloch and Pitts had shown mathematically their information processing ability in 1943. In this thesis, we present a genetic neuro-control scheme for nonlinear systems. Our method is different from those using supervised learning algorithms, such as the backpropagation (BP) algorithm, that needs training information in each step. The contributions of this thesis are the new approach to constructing neural network architecture and its training.
UR - https://www.scopus.com/pages/publications/83755181405
U2 - 10.1007/978-3-642-27180-9_71
DO - 10.1007/978-3-642-27180-9_71
M3 - Conference paper
AN - SCOPUS:83755181405
SN - 9783642271793
T3 - Communications in Computer and Information Science
SP - 591
EP - 596
BT - Grid and Distributed Computing - International Conference, GDC 2011, Held as Part of the Future Generation Information Technology Conference, FGIT 2011, Proceedings
T2 - International Conference on Grid and Distributed Computing, GDC 2011, Held as Part of the 3rd International Mega-Conference on Future-Generation Information Technology, FGIT 2011
Y2 - 8 December 2011 through 10 December 2011
ER -