Course : Machine Learning (ML)
Participants : BSc Mathematics and Data Science students Institution : Sorbonne University Instructor : Dr. Tanujit Chakraborty Teaching Assistantship : Madhurima Panja Timeline : January 2023 to April 2023 Total Teaching : 60 Sessions Email : [email protected] GitHub Page: github.com/ctanujit/MATH-370 |
GIZA PETRONAS BURJ ML COURSES
PYRAMID TOWERS KHALIFA ON INTERNET |
Course Objectives:
The aim of the course is to introduce students to some of the fundamental tools of Data Science and Machine Learning. The course is ideally divided in three parts. In the first part, supervised learning methods for prediction and classification are presented. In particular, the course covers linear regression methods, kernel methods, decision trees and support vector machines. In the second part of the course, unsupervised learning methods are presented, including clustering and spectral PCA. The third and last part of the course ends constitutes an opening on deep learning (neural networks and deep neural networks).
Course Syllabus: Topics to be covered in this course include
Each Theory and Practical Classes are for 2 hours, respectively. Practical classes involves coding from scratch in Python first and then using popular software frameworks and libraries, such as scikit-learn, Keras, Tensorflow, etc. Tutorials involve theoretical exercises (mathematical problems) and problem solving.
1. Introduction to Machine Learning
2. Essential Calculus and Linear Algebra
3. Optimization Techniques for ML
4. Probability Essentials and Parameter Estimation
5. MAP Estimation and Bayesian Inference
6. Basics of Python
7. Learning with Prototypes and K Nearest Neighbors
8. Learning using Decision Trees
9. Introduction to Linear Models and Linear Regression
10. Probabilistic Linear Regression
11. Logistic Regression
12. Generative Models for Supervised Learning
13. Perceptron and Support Vector Machines
14. Nonlinear Learning with Kernels
15. Unsupervised Learning using K-Means Algorithm
16. Hierarchical and Graph Clustering
17. Principal Component Analysis for Dimensionality Reduction
18. Nonlinear dimensionality reduction: Kernel PCA and Manifold Learning
19. EM Algorithm and Latent Variable Models
20. Neural Networks : MLP and Backpropagation
21. Introduction to Deep Neural Networks
22. Bias-Variance Trade-off and Ensemble Learning
23. Reinforcement Learning
24. Semi-supervised Learning and Multi-task Learning
25. Recommendation Systems.
1. Introduction to Machine Learning
2. Essential Calculus and Linear Algebra
3. Optimization Techniques for ML
4. Probability Essentials and Parameter Estimation
5. MAP Estimation and Bayesian Inference
6. Basics of Python
7. Learning with Prototypes and K Nearest Neighbors
8. Learning using Decision Trees
9. Introduction to Linear Models and Linear Regression
10. Probabilistic Linear Regression
11. Logistic Regression
12. Generative Models for Supervised Learning
13. Perceptron and Support Vector Machines
14. Nonlinear Learning with Kernels
15. Unsupervised Learning using K-Means Algorithm
16. Hierarchical and Graph Clustering
17. Principal Component Analysis for Dimensionality Reduction
18. Nonlinear dimensionality reduction: Kernel PCA and Manifold Learning
19. EM Algorithm and Latent Variable Models
20. Neural Networks : MLP and Backpropagation
21. Introduction to Deep Neural Networks
22. Bias-Variance Trade-off and Ensemble Learning
23. Reinforcement Learning
24. Semi-supervised Learning and Multi-task Learning
25. Recommendation Systems.
Evaluation Components:
The evaluation components for the Machine Learning course will be as follows:
1) Homework Assignments - 25% 2) Mid Term Test - 20% 3) Project Work - 25% 4) End Term Test - 30%.
1) Homework Assignments - 25% 2) Mid Term Test - 20% 3) Project Work - 25% 4) End Term Test - 30%.
Textbooks and References:
This course will be taught by using slides, lecture notes, tutorials, papers, and Python notebooks. Some recommended books are listed below (* indicates the most used books in this course). For students, "Dive into Deep Learning" book covers many of the topics on Machine Learning and Deep Learning very easily and coding from scratch in Python (https://d2l.ai/index.html).
- Deisenroth, M. P., Faisal, A. A., & Ong, C. S. (2020). Mathematics for machine learning. Cambridge University Press. (Read Online)
- Friedman J, Hastie T, Tibshirani R. (2017). The Elements of Statistical Learning. Springer series in statistics. (Read Online)
- Bishop, C. M., (2006). Pattern recognition and machine learning*. Springer. (Read Online)
- Murphy, K. P. (2012). Machine learning: a probabilistic perspective*. MIT press. (Read Online)
- Shalev-Shwartz, S., & Ben-David, S. (2014). Understanding machine learning: From theory to algorithms. Cambridge university press. (Read Online)
- Hart, P. E., Stork, D. G., & Duda, R. O. (2000). Pattern classification. Hoboken: Wiley. (Read Online)
- Daumé, H. (2017). A course in machine learning. (Read Online)
- Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep learning*. MIT press. (Read Online)
- Mohri, M., Rostamizadeh, A., & Talwalkar, A. (2018). Foundations of machine learning. MIT press. (Read Online)
- Zhang, A., Lipton, Z. C., Li, M., & Smola, A. J. (2021). Dive into deep learning. (Read Online)
Some Interesting Papers / Webpages For Reading :
• Artificial Intelligence - The Quest for Artificial Intelligence: A History of Ideas and Achievement (2010)
• Machine Learning - Machine learning: Trends, perspectives, and prospects Paper in Science (2015)
• Neural Networks - A Brief History of Neural Nets and Deep Learning (2020)
• Deep Learning - Deep Learning Review Paper in Nature (2015)
• Math Refresher - Mathematics for Machine Learning (2018)
• Machine Learning - Machine learning: Trends, perspectives, and prospects Paper in Science (2015)
• Neural Networks - A Brief History of Neural Nets and Deep Learning (2020)
• Deep Learning - Deep Learning Review Paper in Nature (2015)
• Math Refresher - Mathematics for Machine Learning (2018)
Datasets :
|
Other Links :
|
MUST-known Things:
Classnote, Tutorial and Lab Sessions:
This is a 12 weeks course for L3 Mathematics. All the data and codes used during teaching will be made available in this link:
This is a 12 weeks course for L3 Mathematics. All the data and codes used during teaching will be made available in this link:
Week 1 : Topics:
- Introduction to Machine Learning
- Essential Calculus and Linear Algebra
- Introduction to Python