MATH 6397   Mathematics of Machine Learning (tentative syllabus)


When and Where

    Semester: Spring 2019
    Meeting time: MWF 10-11
    Meeting place: AH 2
    Office Hours: Wed, Fri 11-12 or by appointment

Instructor

 

Course Objectives

Prerequisite

Homework and student assignments


List of lecture notes:

Lecture set 01: What is machine learning? (Scribes: B. Pahari and J. Rodriguez )
Lecture set 02: SVM - part 1 (Scribes: W. Molina and A. Vu)
Lecture set 03: SVM - part 2 (Scribes: A. Zhiliakov and S. Oyeleye)
Lecture set 04: RKHS - part 1 (Scribes: Y. Su and Q. Bai)
Lecture set 05: RKHS - part 2 (Scribes: M. Davies and A. Abouserie)
Lecture set 06: RKHS - part 3 (Scribes: M. Subedi and J. Cortez)
Lecture set 07: Loss functions and their risks (Scribes: H. Zhao and Y. Su)
Lecture set 08: Representer theorems (Scribes: M. Stickler)
Lecture set 09: Basic statistical learning - part 1 (Scribes: A. Niu, Y. Huang, A. Chen)
Lecture set 10: Basic statistical learning - part 2 (Scribes: A. Goligerdian, Y. Palzhanov)
Lecture set 11: Introduction to High Dimensional Data - part 1 (Scribe: N. Fularczyk )
Lecture set 12: Introduction to High Dimensional Data - part 2 (Scribes: K. Safari and S. Thacker )

Final presentations:

1. Super-Convergence: Very Fast Training of Neural Networks Using Large Learning Rates, by W. Molina and K. Safari
2. Relationship between Convolutional Neural Networks and Convolutional Sparse Coding, by B. Pahari and J. Rodriguez
3. Introduction to Convolutional Neural Networks and application to face detection, by Y. Su and A. Vu
4. Auto-encoder interpolation, by S. Oyeleye and A. Zhiliakovy
5. Comparison Study of MLP and SVM, by Q. Bai and Y. Su
6. Quantum Machine Learning in Feature Hilbert Spaces, by N. Fularczyk
7. SVM and SVM Ensembles in Breast Cancer Prediction, by Y. Chen, A. Huanh and A. Niu
8. Metamorphosis of Images in Reproducing Kernel Hilbert Spaces, by H. Zhao
9. Comparison of Loss Functions Used in Classification, by A. Abouserie and M. Stickler
10. An exploration of probabilistic support vector machines, by M.J. Cortez and M. Subedi
11. U-Net: Convolutional Networks for Biomedical Image Segmentation, by M. Davies
12. Solving ill-posed inverse problems using iterative deep neural networks, by A. Goligerdian and Y. Palzhanov
13. Shannon’s Sampling Theorem II: Connections to learning Theory, by S. Thacker

Textbook Information