Machine Learning
Course title: Machine Learning
Code: FEIT01L006
Number of credits (ECTS): 6
Weekly number of classes: 2+2+1+0
Prerequisite for enrollment of the subject: None
Course goals/Competences: Introduction to machine learning and the basic and most common techniques and methods used; providing knowledge and training sufficient for independent solving of practical problems based in artificial intelligence.
Total available number of classes: 180
Curriculum: Introduction. Basic terms and definitions. Intelligent agents. Solving AI problems by searching. Solving problems with constraints. Probability in AI. Bayes theorem. Bayes networks. Learning. Naïve Bayes, linear regression, clustering. Game theory. Minimax, alpha-beta. Neural networks. Learning in neural networks. Solving AI problems in Python.
Literature:
|
Literature |
|||||
|
Compulsory literature |
|||||
|
No. |
Author |
Title |
Publisher |
Year |
|
|
1 |
Stuart J. Russell |
Artificial Intelligence – A Modern Approach |
Prentice Hall |
1995 |
|
|
2 |
L.P.J. Veelenturf |
Analysis and Application of Artificial Neural Networks |
Prentice Hall |
1995 |
|
|
Further literature |
|||||
|
No. |
Author |
Title |
Publisher |
Year |
|
|
1 |
Elaine Rich |
Artificial Intelligence |
McGraw - Hill |
1991 |
|
