Review on the Architecture, Algorithm and Fusion Strategies in Ensemble Learning
Shruti Asmita, K.K. Shukla · International Journal of Computer Applications · 2014
Ensemble Learning is an approach in machine learning to find a predictive model taking into considerations the opinions of various experts.Groups of people can often make better decisions than individuals especially when group members come in with their own biases.This document presents a review on the possible architectures that can be used to build an ensemble model, the techniques in which the opinions of the experts could be combined to give a general improved model and the algorithms for implementing the Ensemble Learning.Comparison of architectures is done on the basis of diversity, classification accuracy and memory consumption.This can be helpful in choosing the options depending on the requirement.In the last part an analysis of ensemble learning algorithms on the basis on Bias and Variance is included.