Advanced Machine Learning
|
Course Objectives
|
| In this course, optimization basis of artificial intelligent algorithms like artificial neural networks and support vector machine and the applications on their solutions is aimed. |
|
Course Content
|
| K-Means, K-NN, Decision trees ID3, C4.5, Bayesian and Naive Bayes , Least squares and linear regression, Perceptron, Adaline, Least Mean Squares, Levenberg- Marquartd and artificial neural networks, Reinforcement Learning, Q-Learning, TD-Learning, Learning Vector Quantization Network, Radial Basis Function Network, Lagrange Method and Support Vector Machine, Principal Component Analysis, Linear Discriminant Analysis, Fuzzy Logic and Fuzzy Inference System. |
|
Course materials
|
- How to Solve It: Modern Heuristics, Z. Michalewicz, D. B. Fogel, Springer, 2004.
- Pattern Recognition and Machine Learning, C. M. Bishop, Springer, 2007.
- Neural Networks and Learning Machines, S. Haykin, Prentice Hall, 2008.
|
|
Assessment
|
|
30% Midterm exam + 30% Presentation + 40% Final Exam
|
|
Prerequisites
|
The student should have taken at least one course about the programming.
|
| Week |
Subjects |
| 1. |
Introduction to Course & Python |
| 2. |
Introduction to machine learning |
| 3. |
Distance-based Clustering and Classification: K-Means and K-NN |
| 4. |
Entropy-based Decision Trees: ID3 and C4.5 |
| 5. |
Probability, Bayesian Theorem, Naive Bayes |
| 6. |
Least squares optimization and linear regression |
| 7. |
Introduction to Artificial Neural Networks: Perceptron and Adaline |
| 8. |
Midterm exam |
| 9. |
Multi-layered artificial neural networks and Backpropagation |
| 10. |
Reinforcement Learning: Q and TD Learning, LVQ |
| 11. |
Mapping and Kernel Functions: RBF Networks |
| 12. |
Optimization by Lagrange Method: Support Vector Machine |
| 13. |
Dimension Reduction: PCA and LDA |
| 14. |
Fuzzy Logic and Fuzzy Inference Systems |
| 15. |
Project Presentations |
| |
Final Exam |
|