Introduction to Machine Learning
Students successfully completing this course will be able to:
• derive standard machine learning algorithms (least squares, logistic regression, PCA, MLP).
• use machine learning algorithms using Python.
Learn how to use machine learning methods for real data. Beginning with the basic of machine learning including linear algebra, probability, linear regression, and logistic regression, and progressing to deep learning methods. In addition to the lectures, hands-on classes develop competencies in practical use of these techniques. Finally, implement these in student-driven machine learning projects (possibly using data provided from OIST units).
Two weekly sessions:
1. Introduction to Machine Learning lecture + Hands-on; Linear Algebra for ML, Vectors and Matrices + Hands-on
2. Probability and Maximum Likelihood estimation +Hands-on; Linear Regression lecture + Hands-on
3. Classification lecture + Hands-on, Nonlinear Regression lecture + Hands-on
4. Mid-term exam; Review of Mid-term exam
5. Feature Selection + Hands-on; Dimensionality Reduction (PCA, CCA, t-SNE) lecture + Hands-on
6. Model Ensemble + Hands-on; Introduction to Deep Learning + Hands-on
7. Graph Neural Network + Hands-on; Representation Learning + Hands-on
8. Project 1; Project2
9. Project 3; Project4
10. Final presentation 1; Final presentation 2
In-term tests 30%, project 70%
85-100 = A, 75-84 = B, 60-75 = C, <60 = F
No prerequisites. However, without some mathematics and programming background, topics like deep learning are hard to follow.
Mathematics for Machine Learning https://mml-book.github.io/
Pattern Recognition and Machine Learning https://www.microsoft.com/en-us/research/uploads/prod/2006/01/Bishop-Pa…
Deep Learning https://www.deeplearningbook.org/
Foundations of Machine Learning https://cs.nyu.edu/~mohri/mlbook/