CONTACT
CONTACT

Machine Learning

Course ID
CSIS1-2
Direction
1st, 2nd, 3rd
Semester
Winter
Type
1st direction elective, 3rd direction elective, 2nd direction mandatory

Learning Outcomes

Upon successful completion of this course, students are expected to have deep understanding of basic machine learning principles, as well as of the most important machine learning methods. They are also expected to have the ability to apply these methods to practical problems with the use of modern software libraries.

Course Content

  • Introduction to machine learning - definitions ορισμοί
  • Generalization, underfitting and overfitting
  • Quick recap of necessary mathematical background (linear algebra, univariate and multivariate calculus, probability theory, optimization theory)
  • Linear Discriminant Analysis
  • Introduction to scikit-learn
  • Quick introduction to data preparation methods
  • Linear regression and the least squares method
  • Linear classification and Generalized Linear Models
  • Nonparametric methods - kNN and kernel methods
  •  Classification and Regression Trees - CART
  •  Ensemble methods - Random Forests, Gradient Boosting Trees, AdaBoost and their variations
  • Presentation of the XGBoost environment
  •  Introduction to Artificial Neural Networks
  •  Introduction to Pytorch
  • Training ANNs and backpropagation

General Skills

Search, analysis and synthesis of data and information with the use of the assorted technologies

Adaptation in new conditions

Decision Making

Independent work

Promoting reasoning and self improvement

Promoting free, creative and deductive reasoning

Learning and Teaching Methods - Evaluation

Teaching methods: On site 

Use of Information and Communication Technologies: Software Development in Python using Numpy, Pandas, scikit-learn, XGBoost, and Pytorch. Data preparation and model development.

Activity Work load
Semester
Lectures 30
Lab exercises 6
Thesis 50
Independent Study 64
Total 150

Assessment

Individual student projects

Literature

 – Stuart Russel, Peter Norvig, “Τεχνητή Νοημοσύνη: Μία Σύγχρονη Προσέγγιση”, 4η
έκδοση, Εκδ. Κλειδάριθμος, 2021
 – Ι. Βλαχάβα, Π. Κεφαλά, Ν. Βασιλειάδη, Φ. Κόκκορα και Η. Σακελλαρίου. “Τεχνητή Νοημοσύνη”, 4η Έκδοση (2020). Εκδοτικός οίκος Εταιρεία αξιοποίησης και διαχείρισης περιουσίας Πανεπιστημίου Μακεδονίας


Journals (indicative):
IEEE Transactions on Pattern Analysis and Machine Intelligence
IEEE Transactions on Neural Networks and Learning Systems
Expert Systems with Applications
Journal of Machine Learning Research
Machine Learning
Journal of Artificial Intelligence Research
Neural Computing and Applications


Conferences (indicative):
Neural Information Processing Systems (NeurIPS)
International Conference on Machine Learning (ICML)
International Conference on Learning Representations (ICLR)
AAAI Conference on Artificial Intelligence (AAAI)
Computer Vision and Pattern Recognition (CVPR)
International Conference on Computer Vision (ICCV)
International Joint Conference on Artificial Intelligence (IJCAI)
European Conference on Machine Learning (ECML)
Asian Conference on Machine Learning (ACML)