Semester A
Mandatory
Machine Learning for Industry
From basic ML techniques to deep learning models and their industrial applications: demand forecasting, anomaly detection, predictive maintenance, and supply chain analysis.
Learning Outcomes
1)
Understanding basic machine learning techniques and their theoretical foundations
2)
Analysis and Understanding of Machine Learning (ML) Algorithms
3)
Implementation of ML techniques using appropriate programming tools (Python, etc.)
4)
Use of evaluation metrics (Precision, Recall, F1-score, ROC-AUC) to evaluate models
5)
ML application for demand forecasting, anomaly detection, and predictive maintenance
6)
Combining ML techniques to solve problems across different scientific fields
7)
Understanding the use of ML techniques in industrial practice
8)
Conducting a comprehensive literature review on ML techniques
General Skills
Adapting to new situations
Decision-making
Independent project
Team project
Syllabus
Week
Topic
1
Introduction to Machine Learning and Types of Learning
2
Regression Methods
3
Data Classification and Adaptation Using k-Nearest Neighbors
4
Artificial Neural Networks and Their Types
5
Radial Basis Function Networks and the k-Means Algorithm
6
Support Vector Machines
7
Decision Trees
8
Feature Selection and Construction Techniques
9
Deep Learning Models
10
Recurrent Neural Networks
11
Bayesian Neural Networks
12
Ensemble Methods
13
Assignment of Final Projects
Evaluation & Workload
Bibliographic Assignment
Project Implementation
Independent Study
Bibliography
Diamantaras & Botsis
K. Diamantaras
Christopher Bishop
Journal of Machine Learning Research
IEEE Trans. on Pattern Analysis & Machine Intelligence
IEEE Trans. on Neural Networks and Learning Systems
Expert Systems with Applications
Neurocomputing — Elsevier
Course Information
Semester
Α΄
Minutes per Week
180
Type
Specialized Knowledge
Requirements
Course Format
Synchronous
Asynchronous
Remote
e-class
Technologies & Tools
Python
scikit-learn
TensorFlow
Keras
PyTorch
XGBoost
Random Forest
SVM
KNN