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
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;
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
DOI :
10.1109/ANN.1991.213500
