fi3271-01 2024-2
FI3271 Data Analysis with Machine Learning is a 3-hours course given in about 15-16 weeks. It is a part of 2024 curriculum .
topics
- Computational thinking and algorithm design
- Concepts in machine learning: supervised and unsupervised learning
- Probability distributions and their applications
- Linear models for regression and classification
- Sampling methods and their role in data analysis
- Artificial neural networks: structure and training
- Gaussian process regression for atomic force field modeling
- Genetic algorithms and evolutionary computation
- Bayesian optimization and its applications
learning outcome
- Understand and explain the basic concepts of computational thinking
- Design algorithms to solve problems involving physical systems and data
- Apply machine learning techniques to analyze data from physical systems
- Present scientific findings clearly in both written reports and oral presentations
- Collaborate effectively in teams and work independently when needed
conducted plan (fm)
Week | Topic ↓ Subtopic |
---|---|
Computational thinking and algorithm design | |
01.1 | Concept of computational thinking |
Abstraction and decomposition | |
Pattern recognition | |
01.2 | Algorithmic thinking |
Sampling methods and their role in data analysis | |
02.1 | Data mining |
Data preprocessing | |
Linear models for regression and classification | |
02.2 | Linear regression |
04.1 | Classification with Support Vector Machine (SVM) |
Quiz | |
04.2 | Support Vector Machine kernels |
Concepts in machine learning: supervised and unsupervised learning | |
03.1 | Principal Component Analysis 1 |
03.2 | Principal Component Analysis 2 |
05.1 | Classification with k-nearest neighbors (k-NN) algorithm 1 |
05.2 | Classification with k-nearest neighbors (k-NN) algorithm 2 |
Artificial neural networks: structure and training | |
06.1 | Concept of Artificial Neural Network (ANN) |
06.2 | Architecture of Multi-Layer Perceptron (MLP) 1 |
07.1 | Architecture of Multi-Layer Perceptron (MLP) 2 |
07.2 | ANN basic method hands-on |
08.1 | Midterm |
08.2 | ANN hierarchy design |
Independent assignment |
tentative plan (sv)
Week | Topic ↓ Subtopic |
---|---|
Probability distributions and their applications | |
09.1 | Introduction to probability distributions |
Common probability distributions in Machine Learning | |
09.2 | Applications in Machine Learning |
Gaussian process regression for atomic force field modeling | |
10.1 | Background concepts |
Representing atomic environments | |
Model training and prediction | |
Force field construction | |
10.2 | applications |
Software and tools | |
Limitations and challenges | |
Genetic algorithms and evolutionary computation | |
11.1 | Foundations of Evolutionary Computation |
Genetic Algorithms (GAs) | |
Evolutionary Strategies (ES) | |
Genetic Programming (GP) | |
Differential Evolution (DE) | |
Other Evolutionary Algorithms | |
Hybrid and Memetic Algorithms | |
11.2 | Theoretical Aspects |
Applications | |
Tools and libraries | |
Benchmark problems | |
Recent advances and research trends | |
Bayesian optimization and its applications | |
12.1 | Foundations of Bayesian optimization |
Advanced techniques | |
Algorithmic implementations | |
12.2 | Applications |
Applications in Machine Learning | |
Applications in Science and Engineering | |
Applications in Business and Operations | |
Software and tools | |
Recent research trends | |
Research-Based Learning (RBL) | |
13.1 | Topics proposing and discussion |
Working group creation | |
13.2 | Short presentasion |
14.1 | Progress report presentation 1 |
14.2 | Progress report presentation 2 |
15.1 | Progress report presentation 3 |
15.2 | Progress report presentation 4 |
16.1 | Final report presentation |
16.2 | Publishing final report on Medium, OSF, YouTube |
notes
- Information from SIX are gathered and mixed with lecturers discussion.
- There four references from course syllabus 1, 2, 3, 4, where the first two are main references, while the others are additional ones.
- There is an additional reference for information related to probability distributions 5.
refs
Christopher M. Bishop, “Pattern Recognition and Machine Learning”, 1st edition, Springer, 2006, url https://isbnsearch.org/isbn/9780387310732 2dn86 [20250420]. ↩︎
S. Haykin, “Neural Networks and Learning Machines”, 3rd edition, Pearson Education, 2009, url https://isbnsearch.org/isbn/9780131471399 b69e4 [20250420]. ↩︎
Stuart J. Russell, Peter Norvig, “Artificial Intelligence: A Modern Approach”, 3rd edition, Pearson Education, 2016, url https://isbnsearch.org/isbn/9780136042594 s3keu [20250420]. ↩︎
Alberto Artasanchez, Prateek Joshi, “Artificial Intelligence with Python: Your complete guide to building intelligent apps using Python 3.x”, 2nd edition, Packt Publishing, 2020, url https://isbnsearch.org/isbn/9781839219535 eb3p2 [20250420]. ↩︎
T. T. Soong, “Fundamentals of Probability and Statistics for Engineers”, Wiley, 1st edition, 2004, url https://isbnsearch.org/isbn/9780470868140 [20250420]. ↩︎