Title :
Gradient Learning Algorithm for Ensembling Neural Network
Author :
Meng, Jiang ; An, Kun
Author_Institution :
Sch. of Mech. Eng. & Automatization, North Univ. of China, Taiyuan
Abstract :
Aimed at similarity between neural network ensemble and simple neural network, a novel gradient learning algorithm for ensemble (GLAENN) is presented based on the gradient descent method. The new algorithm can improve the generalization error by modifying subnet weights after the ensemble subnets are trained individually. The simulation results indicate GLAENN is of similar function to GASEN but with a different idea; further, it is of better generalization performance than GASEN, bagging and single network
Keywords :
gradient methods; learning (artificial intelligence); neural nets; generalization error; gradient descent method; gradient learning algorithm; neural network ensemble; subnet weight; Bagging; Genetic algorithms; Humans; Least squares approximation; Mechanical engineering; Network topology; Neural networks; Neurons; Optimization methods; Training data; GASEN; Neural network ensemble; generalization performance; gradient descent;
Conference_Titel :
Control, Automation, Robotics and Vision, 2006. ICARCV '06. 9th International Conference on
Conference_Location :
Singapore
Print_ISBN :
1-4244-0341-3
Electronic_ISBN :
1-4214-042-1
DOI :
10.1109/ICARCV.2006.345247
