Content: The aim of the course is to give the student a general view of the field of machine learning through the study of the major models and learning methods with and without supervision. The course also offers basic mathematical background necessary to understand the basic mechanisms of learning as well as the capabilities and limitations of the learning models.
Course description. The course will cover th following topics:
Introduction
Basic concepts
Learning and Generalization
Supervised Learning
Mathematical Background
Neural models
Probabilistic models, Bayesian models
Support vector machines
Feature selection
Mixing models, bagging, boosting.
Unsupervised Learning
Principal Component Analysis (PCA)
Clustering
Evaluation: the course will be evaluated through a project.
Objectives: The course offers an introduction to the rapidly evolving field of machine learning. The field falls in the general area of machine intelligence and is used by the majority of computer applications.
With the successful completion of the course, the student:
• Will acquire essential knowledge regarding the types of machine learning problems as well as the basic methods applicable for each type of problems
• Will acquire the necessary skills for the implementation of machine learning methods in high level programming languages
• Will acquire the ability to analyze problems and applications that require the use of machine learning methods
• Will acquire the ability to apply suitable machine learning methods to any specific problem domain of interest
1. C. Bishop, Pattern Recognition and Machine Learning, Springer 2006
2. S. Haykin, Neural Networks and Learning Machines (3rd Edition), Prentice Hall, 2008
3. J. Shawe-Taylor and N. Cristianini, Kernel Methods for Pattern Analysis, Cambridge University Press, 2004
4. R. O. Duda, P. E. Hart, and D. G. Stork, Pattern Classification (2nd Edition), Wiley Interscience, 2000
