Semi-supervised feature selection using mean absolute deviation

High-dimensional datasets can cause problems to learning steps (Ex. Classification or Clustering). Feature reduction helps in reducing the number of a feature in datasets and in turn, makes the learning steps algorithms perform faster and yield better results than using the whole features in a dataset. Also using the semi-supervised information to an unsupervised feature selection algorithm has shown to have yield better result. The thesis looks into the Mean Absolute Deviation (MAD) which uses unsupervised information and try to use the semi-supervised learning information to make improvements. The method used in this thesis is named Mean Absolute Deviation New (MADN). The new method has been shown to be an improvement over MAD method on face datasets and to be comparative to sparse datasets.