MMAML 2016 - Special Session on Multiple Model Approach to Machine Learning

Ensemble methods have gained great attention of scientific community over the last several years. Multiple models have been theoretically and empirically shown to provide significantly better performance than their single base models. Ensemble algorithms have found their application in various real word problems ranging from person recognition through medical diagnosis and text classification to financial forecasting. The MMAML 2016 Special Session at the 8th Asian Conference on Intelligent Information and Database Systems (ACIIDS 2016) is devoted to the ensemble methods addressing classification, prediction, and clustering problems and their application to Big Data and small data sets as well as data streams and stationary data sets. We want to offer an opportunity for researchers and practitioners to identify new promising research directions as well as to publish recent advances in this area. The scope of the MMAML 2016 includes, but is not limited to the following topics:
? Theoretical framework for ensemble methods
? Ensemble learning algorithms: bagging, boosting, stacking, etc.
? Ensemble methods in clustering
? Dealing with Big Data and small data sets
? Subsampling and feature selection in multiple model machine learning
? Diversity, accuracy, interpretability, and stability issues
? Homogeneous and heterogeneous ensembles
? Hybrid methods in prediction and classification
? Incremental, evolving, and online ensemble learning
? Mining data streams using ensemble methods
? Ensemble methods for dealing with concept drift
? Multi-objective ensemble learning
? Ensemble methods in agent and multi-agent systems
? Implementations of ensemble learning algorithms
? Assessment and statistical analysis of ensemble models
? Applications of ensemble methods in business, engineering, medicine, etc