DocumentCode
3147603
Title
Query based learning in a multilayered perceptron in the presence of data jitter
Author
Oh, Seho ; Marks, Robert J., II ; El-Sharkawi, M.A.
Author_Institution
Dept. of Electr. Eng., Washington Univ., Seattle, WA, USA
fYear
1991
fDate
23-26 Jul 1991
Firstpage
72
Lastpage
75
Abstract
Stochastically perturbed feature data is said to be jittered. Jittered data has a convolutional smoothing effect in the classification (or regression) space. Parametric knowledge of the jitter can be used to perturb the training cost function of the neural network so that more efficient training can be performed. The improvement is more striking when the addended cost function is used in a query based learning procedure
Keywords
learning (artificial intelligence); neural nets; addended cost function; convolutional smoothing effect; data jitter; multilayered perceptron; query based learning; training; training cost function; Convolution; Cost function; Input variables; Jitter; Multilayer perceptrons; Neural networks; Probability density function; Random number generation; Taylor series; Training data;
fLanguage
English
Publisher
ieee
Conference_Titel
Neural Networks to Power Systems, 1991., Proceedings of the First International Forum on Applications of
Conference_Location
Seattle, WA
Print_ISBN
0-7803-0065-3
Type
conf
DOI
10.1109/ANN.1991.213500
Filename
213500
Link To Document