Due to the high demand for CS 6316 from our graduate students, we will not admit undergraduate students until we are sure that there are enough spaces for graduate students. Thank you for the understanding!

## 1. Basic Information

- Instructor: Yangfeng Ji
- Semester: Spring 2022
- Location: Olsson Hall 120
- Time: Tuesday and Thursday 5:00 PM - 6:15 AM
- TA:
- Stephanie Schoch
- Wanyu Du
- Dane Williamson
- Andrew Wang

- Office Hours: TBA

## 2. Highlights

## 3. Course Description

- The goal of this course is to understand basic concepts and models in machine learning. Coding or implementing a machine learning model in detail will
**not**be an emphasis of this course. - Deep learning (or neural network modeling) will only be a small part of this course: two lectures in one week.

### 3.1 Topics

Most of the course materials (and assignments) are adopted from Shalev-Shwartz and Ben-Davidâ€™s textbook on machine learning. Particularly, the topics overed in this course are:

- Introduction to learning theory
- Linear classification and regression
- Support vector machines and kernel methods
- Model selection and validation
- Neural networks and deep learning
- Optimization
- Generative modeling

For more information about this course, please checkout the [schedule](schedule.

### 3.2 Prerequisites

**Calculus and Linear Algebra**

Multivariable derivatives, matrix/vector notations and operations; singular value decomposition, etc.**Probability and Statistics**

Mean and variance, multinomial distribution, conditional dependence, maximum likelihood estimation, Bayes theorem, etc.**Proficiency in Python**

This course requires some programming in both homeworks and the final project. The preference of programming language for this course is Python (with some additional packages like Scipy, Sklearn, Tensorflow, and PyTorch), but it is also fine to use other programming languages (e.g., C/C++/Java), if you have lots of experience of it.

### 3.3 Textbook

- [UML] Shalev-Shwartz and Ben-David. Understanding Machine Learning: From Theory to Algorithms. 2014
- [DL] Goodfellow, Bengio, and Courville. Deep Learning. 2016

**Additional**

- [PRML] Bishop. Pattern Recognition and Machine Learning. 2006
- [MRT] Mohri, Rostamizadeh, and Talwalkar. Foundations of Machine Learning. 2nd Edition. 2018

## 4. Assignments and Final Project

**Homework (72%)**:- There will be
**four**homeworks and each of them is worth 18%. - Although collaboration on homework is
*not*encouraged, students are allowed to discuss with their classmates. But, directly copying answers from others is definitely considered as plagiarism.

- There will be
**Project (25%)**:

There is only one course project and the credit breaks down to four parts- Project proposal: 8%
- Final project presentation: 7%
- Final project report: 10%
- Other than using the machine learning libraries including Sklearn, PyTorch, Tensorflow, students need to implemented the rest of the proposed model by themselves. Copying code from any resources (e.g., Github, Bitbucket, and Gitlab) is prohibited and will be considered as plagiarism.
- Students should team up for this project, each group can have up to four students.

**Class participation (3%)**:

At*three*randomly-selected lectures in this semester, we will take attendance. Each is worth 1%.

### 4.1 Grading Policy

For other information, please visit this page