TY - GEN
T1 - Semi batch learning with store management using enhanced conjugate gradient
AU - Asirvadam, V. S.
AU - Izzeldin, Huzaifa T A
AU - Saad, Nordin
AU - Mcloone, Sean F.
PY - 2012/1/25
Y1 - 2012/1/25
N2 - This paper explores the performance of sliding-window based training, termed as semi batch, using multilayer perceptron (MLP) neural network in the presence of correlated data. The sliding window training is a form of higher order instantaneous learning strategy without the need of covariance matrix, usually employed for modeling and tracking purposes. Sliding-window framework is implemented to combine the robustness of offline learning algorithms with the ability to track online the underlying process of a function. This paper adopted sliding window training with recent advances in conjugate gradient direction with application of data store management e.g. simple distance measure, angle evaluation and the novel prediction error test. The simulation results show the best convergence performance is gained by using store management techniques.
AB - This paper explores the performance of sliding-window based training, termed as semi batch, using multilayer perceptron (MLP) neural network in the presence of correlated data. The sliding window training is a form of higher order instantaneous learning strategy without the need of covariance matrix, usually employed for modeling and tracking purposes. Sliding-window framework is implemented to combine the robustness of offline learning algorithms with the ability to track online the underlying process of a function. This paper adopted sliding window training with recent advances in conjugate gradient direction with application of data store management e.g. simple distance measure, angle evaluation and the novel prediction error test. The simulation results show the best convergence performance is gained by using store management techniques.
KW - back-propagation
KW - conjugate gradient
KW - data store management
KW - multilayer perceptron
KW - sliding-window learning
UR - http://www.scopus.com/inward/record.url?scp=84856034373&partnerID=8YFLogxK
U2 - 10.1007/978-3-642-26001-8_9
DO - 10.1007/978-3-642-26001-8_9
M3 - Conference contribution
AN - SCOPUS:84856034373
SN - 9783642260001
VL - 136 LNEE
T3 - Lecture Notes in Electrical Engineering
SP - 61
EP - 67
BT - Lecture Notes in Electrical Engineering
T2 - 2nd International Conference of Electrical and Electronics Engineering, ICEEE 2011
Y2 - 1 December 2011 through 2 December 2011
ER -