Machine Learning

Learning Outcomes

On successful completion of this Course, students will be able to: Develop a comprehensive understanding of concepts, techniques and algorithms of machine learning in the supervised learning framework to solve regression and classification problems; Apply learning theories to design effective and efficient models of the learning machines; Evaluate the performance of different models in order to choose the best using model selection and regularization techniques; Develop a comprehensive understanding of concepts, techniques and algorithms of machine learning in the unsupervised learning framework for probability density estimation and data clustering problems; Indentify and apply unsupervised learning methods for dimensionality reduction of the data using factor, principle component and independent component analysis; Indentify current frontiers of machine learning to propose certain research topic in the field of computational intelligence.

Topics

1. Introduction of machine learning and supervised learning frameworks
2. Classification: Discriminative and generative Algorithms
3. Artificial Neural Networks
4. Support Vector Machines
5. Learning Theory
6. Model Selection and Regularization
7. Unsupervised Learning and Clustering
8. Mixture of Gaussians
9. The EM Algorithm
10. Factor Analysis and Principal Components Analysis
11. Independent Components Analysis
12. Current frontiers in machine learning