Information Package / Course Catalogue
Machine Learning and Artificial Intelligence in Physics
Course Code: FİZ210
Course Type: Area Elective
Couse Group: First Cycle (Bachelor's Degree)
Education Language: Turkish
Work Placement: N/A
Theory: 3
Prt.: 0
Credit: 3
Lab: 0
ECTS: 4
Objectives of the Course

Introduce and apply machine learning, artificial intelligence, and optimization methods to physical problems.

Course Content

Data analysis with Python, machine learning, optimization methods, and artificial intelligence applications to physical problems.

Name of Lecturer(s)
Lec. Arash MOBARAKI
Learning Outcomes
1.Be able to define the basic concepts of artificial intelligence and machine learning.
2.Be able to use the Python programming language for scientific data analysis and visualization.
3.Be able to apply basic machine learning algorithms (regression, classification, clustering).
4.Be able to use optimization concepts and global optimization methods (e.g., PSO) in physical problems.
5.Be able to understand neural networks and perform basic applications on physical data.
6.Be able to develop data-driven approaches suitable for physical problems and make modeling and predictions.
Recommended or Required Reading
1.Machine Learning for Physics and Astronomy (Viviana Acquaviva)
2.Introduction to Machine Learning with Python (Andreas C. Müller, Sarah Guido)
3.Machine Learning with Python (Ömer Deperlioğlu, Utku Köse)
Weekly Detailed Course Contents
Week 1 - Theoretical
Introduction to Artificial Intelligence and Machine Learning
Week 2 - Theoretical
Mathematical Foundations: Vectors, Matrices, Derivatives, Gradients
Week 3 - Theoretical
Python and Fundamentals of Scientific Computing I
Week 4 - Theoretical
Python and Fundamentals of Scientific Computing II
Week 5 - Theoretical
Introduction to Machine Learning
Week 6 - Theoretical
Regression and Classification
Week 7 - Theoretical
Model Accuracy and Validation
Week 8 - Theoretical
Topic review (Midterm exam)
Week 9 - Theoretical
Physics Application: Molecular Dynamics and Potentials
Week 10 - Theoretical
Optimization Concepts
Week 11 - Theoretical
Learning Force Fields with ML
Week 12 - Theoretical
Global Optimization Methods
Week 13 - Theoretical
Neural Networks and PyTorch
Week 14 - Theoretical
Time Series and Sequential Data Modeling in Physics
Assessment Methods and Criteria
Type of AssessmentCountPercent
Midterm Examination1%20
Final Examination1%50
Assignment5%30
Workload Calculation
ActivitiesCountPreparationTimeTotal Work Load (hours)
Lecture - Theory141356
Assignment50210
Midterm Examination112214
Final Examination118220
TOTAL WORKLOAD (hours)100
Contribution of Learning Outcomes to Programme Outcomes
PÇ-1
PÇ-2
PÇ-3
PÇ-4
PÇ-5
PÇ-6
PÇ-7
PÇ-8
PÇ-9
PÇ-10
PÇ-11
PÇ-12
PÇ-13
PÇ-14
OÇ-1
1
1
1
1
3
5
3
2
3
5
1
2
1
4
OÇ-2
4
5
2
4
3
5
3
2
3
5
1
3
4
4
OÇ-3
4
5
3
5
3
5
3
2
3
5
1
3
3
4
OÇ-4
1
4
4
4
3
5
3
2
3
5
1
2
1
4
OÇ-5
4
5
4
4
3
5
4
2
3
5
1
3
3
4
OÇ-6
3
4
3
3
3
5
4
2
3
5
1
3
3
4
Adnan Menderes University - Information Package / Course Catalogue
2026