Back to my homepage

---

Course information [Syllabus]

This is a graduate-level course on the machine learning branch of classification, covering the following topics: 

• Instance-based Methods
• Discriminant Analysis
• Logistic Regression
• Support Vector Machine
• Kernel Methods
• Ensemble Methods
• Neural Networks

all based on the benchmark dataset of MNIST Handwritten Digits. Such a teaching strategy was partly inspired by Michael Nielsen's free online book - Neural Networks and Deep Learning, which notes explicitly that this dataset hits a ``sweet spot'' - it is challenging, but ``not so difficult as to require an extremely complicated solution, or tremendous computational power''. In addition, the digit recognition problem is very easy to understand, yet practically important.

Prerequisites: Math 164 and Math 250

Technology requirements: 

• Zoom: Class meetings will be on Zoom [Click here to register].
• Canvas: Assignments and their grades will be posted in Canvas (accessible also via http://one.sjsu.edu/).
• Proctorio: Tests will be delivered via Proctorio.
• Piazza: This course will use Piazza as the bulletin board. Please post all course-related questions there. 

Recommended readings:

1. James, Witten, Hastie and Tibshirani (2017), “An Introduction to Statistical Learning with Applications in R”, Springer 
2. Hastie, Tibshirani, and Friedman (2009), “The Elements of Statistical Learning: Data Mining, Inference, and Prediction”, Springer-Verlag 
3. Nielson (2015), “Neural Networks and Deep Learning”, Determination Press
4. Goodfellow, Bengio, and Courville (2016), “Deep Learning”, MIT Press
   

---

Course progress

Lecture Slides		Further Reading
0	Introduction [slides]	Math 250 (formerly 253) course page
1	Instance-based classifiers [slides]	Sections 2.2.3 and 5.1 of recommended reading 1
2	Dimension reduction for classification [slides]	2DLDA paper
3	Bayes classifiers [slides]	Section 4.4 of recommended reading 1
4	Logistic regression [slides]	Section 4.3 of recommended reading 1
5	Support vector machine [slides]	[Chapter 9 of recommended reading 1] [Lagrange Dual]
6	Evaluation criteria [slides]
7	Ensemble learning [slides]	[Trevor Hastie's slides] [Adele Cutler's lecture] [Chapter 8 of textbook]
8	Neural networks [slides]	[Michael Nielsen’s book] [Olga Veksler’s lecture] [Perceptron]
9	Introduction to deep learning [slides]	Standford CS 231n course page