DocumentCode :
396697
Title :
Regularization and Feedforward artificial neural network training with noise
Author :
Chandra, Pravin ; Singh, Yogesh
Author_Institution :
Sch. of Inf. Technol., G.G.S. Indraprastha Univ., Delhi, India
Volume :
3
fYear :
2003
fDate :
20-24 July 2003
Firstpage :
2366
Abstract :
Regularization is a method used for controlling the complexity of models. Explicit regularization uses a modifier term, incorporating a-priori knowledge about the function to be approximated by Feedforward Artificial Networks, that is added to the risk functional and implicit regularization where noise is added to the system variables during training, are two of the commonly used techniques for model complexity control. The relationship between these two type of regularization is explained. A regularization term is derived based on the general noise model. The interplay between the various noise mediated regularization terms is described.
Keywords :
circuit noise; computational complexity; feedforward neural nets; function approximation; learning (artificial intelligence); feedforward artificial neural network training; function approximation; general noise model; model complexity control; regularization; risk function; Artificial neural networks; Backpropagation algorithms; Computer errors; Euclidean distance; Information technology; Input variables; Minimization methods; Phase noise; Supervised learning; Training data;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Neural Networks, 2003. Proceedings of the International Joint Conference on
ISSN :
1098-7576
Print_ISBN :
0-7803-7898-9
Type :
conf
DOI :
10.1109/IJCNN.2003.1223782
Filename :
1223782
Link To Document :
بازگشت