Machine Learning Principles and Methods

Machine Learning Principles and Methods [8th semester]

Course code 1802. Scientific area course - Mandatory. Area: Data Management - Artificial Intelligence (DMAI). Suggested prerequisite courses: (1301) Probability Theory and Statistics, (1101) Mathematics É, (1201) Mathemetics ÉÉ

The aim of this course is to introduce the student to the basic principles and problems of machine learning such as pattern recognition, value prediction, and clustering. The necessary mathematical background is given including the basic programming tools for the implementation of and application of the ML algorithms. With the successful completion of the course the student will be able to:

• Know the basic methods of Machine Learning and their field of application
• Understand the basic problem types where machine learning can be applied
• Analyze simple learning problems and apply the appropriate methods for their solution
• Implement the basic ML models using the appropriate programming tools
• Evaluate the performance of machine learning models

• Introduction to Machine Learning, basic concepts, the problems of pattern recognition regression, clustering and feature extraction
• Useful mathematical concepts from linear algebra, matrix theory, eigenvalue decomposition, probability theory, and optimization theory
• Generalization, the cross-validation method
• Introduction to Artificial Neural Networks, the linear neuron, the Perceptron, and ADALINE models
• Multi-Layer Neural Networks, the Back-Propagation learning algorithm
• Competitive Learning, Self-organizing networks
• Basic Recurrent models, associative memory, the Hopfield model
• Support Vector Machines, the concept of margin, linear and nonlinear kernels, support vector regression
• Basic clustering methods, the k-means algorithm
• Feature extraction
• Principal Component Analysis (PCA), Factor Analysis

Course material:

Evaluation:

• Final written exam with a combination of multiple-choice questions, short answer questions, and problem-solving questions.
• Optional exercises

Bibliography

1. Êùíóôáíôßíïò ÄéáìáíôÜñáò, ÄçìÞôñçò Ìðüôóçò, "Ìç÷áíéêÞ ÌÜèçóç", Åêäüóåéò ÊëåéäÜñéèìïò ÅÐÅ, ¸êäïóç: 1ç/2019, ISBN: 978-960-461-995-5, Êùäéêüò Âéâëßïõ óôïí Åýäïîï: 86198212
2. Êùíóôáíôßíïò ÄéáìáíôÜñáò, "Ôå÷íçôÜ ÍåõñùíéêÜ Äßêôõá", Åêäüóåéò ÊëåéäÜñéèìïò ÅÐÅ, ¸êäïóç: 1ç/2007, ISBN: 978-960-461-080-8, Êùäéêüò Âéâëßïõ óôïí Åýäïîï: 13908
3. Bishop, Christopher M., "Pattern recognition and machine learning", Springer, 2006