Yi Hong

The University of Georgia

CSCI 4360/6360: Data Science II

Overview: Nowadays we are drowning in data and seeking techniques to extact information from our collected data. In this data science course, we will discuss some technqiues that are commonly used in data analytics. In particular, we will cover the background and fundamentals in data science, basic and advanced machine learning algorithms, as well as deep neural networks. In the end of this course, the students are able to master basic concepts, classical techniques, and useful tools in data science, and are able to analyze their data using the techniques covered in this course.

Course Information

  • Section numbers: 41968/41969

  • Class meetings: Online (Asynchronous); lecture videos will be released in the mornings of the meeting days.

  • Instructor: Yi Hong (yi.hong -at- uga.edu)

  • Office hours: TR 9:00am - 10:00am or by appointment

  • Course webpage: http://cobweb.cs.uga.edu/~yihong/CSCI4360-6360-Fall2020.html

Prerequisites

  • CSCI 3360

Grading

  • Homework (40%, 5 assignments, each 8%)

  • Small Project (15%, implementing a selected technique from scratch)

  • Final Project (40%, including proposal (5%), update (5%), presentation (15%, pre-recorded), and write-up (15%))

  • Participation (5%, answering questions in the end of the lecture videos, five times, each 1%)

There is no exam.

Late Policy: 1 day late (10% off), 2 (20% off), 3 (30% off). Late submissions are not accepted after 3 late days.

Grading scale: A: [93% - 100%], A-: [90% - 93%), B+: [87% - 90%), B: [83% - 87%), B-: [80% - 83%), C+: [77%, 80%), C:[70%, 77%), C-:[65% - 70%), D:[60% - 65%), F: [0% - 60%).

Reference Books

  • Joel Grus. Data Science from Scratch: First Principles with Python. Second Edition (2019), O'Reilly.

  • Aurelien Geron. Hands-on Machine Learning with Scikit-Learn, Keras & TensorFlow: Concepts, Tools, and Techniques to Build Intelligent Systems. Second Edition (2019), O'Reilly.

Tentative Schedule

Date Topic Reading Presenter To Do
Week 0 Aug 20 (R) Course Introduction and Overview -- Yi --
Week 1 Background and Fundamentals
Aug 24 (M) Python Crash Course I Joel Grus' book, Chapter 2-3 Yi --
Aug 25 (T) Python Crash Course II Joel Grus' book, Chapter 2-3 Yi --
Aug 27 (R) Math and Statistics Background I Joel Grus' book, Chapter 4-7 Yi Participation Questions Due at 11:59pm ET on Sunday
Week 2 Aug 31 (M) Math and Statistics Background II Joel Grus' book, Chapter 4-7 Yi --
Sep 1 (T) Math and Statistics Background III Joel Grus' book, Chapter 4-7 Yi --
Sep 3 (R) Fundamentals of Machine Learning I Joel Grus' book, Chapter 8, 11
Aureline Geron's book, Chapter 1, 2, 4
Yi Homework 1 Handout
Participation Questions Due at 11:59pm ET on Sunday
Week 3 Sep 7 (M) Labor Day, No Class -- -- --
Sep 8 (T) Fundamentals of Machine Learning II Joel Grus' book, Chapter 8, 11
Aureline Geron's book, Chapter 1, 2, 4
Yi --
Basic Machine Learning Algorithms
Sep 10 (R) Classification I Joel Grus' book, Chapter 12, 13, 16
Aureline Geron's book, Chapter 3, 5
Yi Participation Questions Due at 11:59pm ET on Sunday
Week 4 Sep 14 (M) Classification II Joel Grus' book, Chapter 12, 13, 16
Aureline Geron's book, Chapter 3, 5
Yi --
Sep 15 (T) Classification III Joel Grus' book, Chapter 12, 13, 16
Aureline Geron's book, Chapter 3, 5
Yi --
Sep 17 (R) Regression I Joel Grus' Book, Chapter 14-15 Yi Homework 1 Due
Participation Questions Due at 11:59pm ET on Sunday
Week 5 Sep 21 (M) Regression II Joel Grus' Book, Chapter 14-15 Yi --
Sep 22 (T) Regression III Joel Grus' Book, Chapter 14-15 Yi --
Sep 24 (R) Paper Reading "SVM-KNN: Discriminative Nearest Neighbor Classification for Visual Category Recognition" Yi Final Project Proposal Due
Homework 2 Handout
Participation Questions Due at 11:59pm ET on Sunday
Week 6 Sep 28 (M) Unsupervised Algorithms I Joel Grus' Book, Chapter 12, 20
Aurelien Geron's Book, Chapter 8-9
Yi --
Sep 29 (T) Unsupervised Algorithms II Joel Grus' Book, Chapter 12, 20
Aurelien Geron's Book, Chapter 8-9
Yi --
Oct 1 (R) Unsupervised Algorithms III Joel Grus' Book, Chapter 12, 20
Aurelien Geron's Book, Chapter 8-9
Yi Participation Questions Due at 11:59pm ET on Sunday
Week 7 Oct 5 (M) Paper Reading and Discussion "Face Recognition Using Kernel Eigenfaces" Yi --
Advanced Machine Learning Algorithms
Oct 6 (T) Decision Trees & Random Forests I Joel Grus' Book, Chapter 17
Aurelien Geron's Book, Chapter 6-7
Yi --
Oct 8 (R) Decision Trees & Random Forests II Joel Grus' Book, Chapter 17
Aurelien Geron's Book, Chapter 6-7
Yi Homework 2 Due
Homework 3 Handout
Participation Questions Due at 11:59pm ET on Sunday
Week 8 Oct 12 (M) Decision Trees & Random Forests III Joel Grus' Book, Chapter 17
Aurelien Geron's Book, Chapter 6-7
Yi --
Oct 13 (T) Paper Reading and Dicussion "XGBoost: A Scalable Tree Boosting System" Yi --
Deep Neural Networks
Oct 15 (R) ANN I Aurelien Geron's Book, Chapter 10-11 Yi Participation Questions Due at 11:59pm ET on Sunday
Week 9 Oct 19 (M) ANN II Aurelien Geron's Book, Chapter 10-11 Yi --
Oct 20 (T) Paper Reading and Discussion "Deep Learning" Yi --
Oct 22 (R) Data Processing Joel Grus' Book, Chapter 9-10
Aurelien Geron's Book, Chapter 13
Yi Homework 3 Due
Participation Questions Due at 11:59pm ET on Sunday
Week 10 Oct 26 (M) CNN I Aurelien Geron's Book, Chapter 14 Yi --
Oct 27 (T) CNN II Aurelien Geron's Book, Chapter 14 Yi --
Oct 29 (R) CNN III Aurelien Geron's Book, Chapter 14 Yi --
Week 11 Nov 2 (M) Paper Reading and Dicussion "Fully Convolutional Networks for Semantic Segmentation" Yi --
Nov 3 (T) RNN I Aurelien Geron's Book, Chapter 15 Yi Final Project Update Due
Nov 5 (R) RNN II Aurelien Geron's Book, Chapter 15 Yi Homework 4 Handout
Participation Questions Due at 11:59pm ET on Sunday
Week 12 Nov 9 (M) RNN III Aurelien Geron's Book, Chapter 15 Yi --
Nov 10 (T) Paper Reading and Dicussion "CNN-RNN: A Unified Framework for Multi-label Image Classification" Yi --
Nov 12 (R) Autoencoder & GANs I Aurelien Geron's Book, Chapter 17 Yi Participation Questions Due at 11:59pm ET on Sunday
Week 13 Nov 16 (M) Autoencoder & GANs II Aurelien Geron's Book, Chapter 17 Yi --
Nov 17 (T) Autoencoder & GANs III Aurelien Geron's Book, Chapter 17 Yi --
Nov 19 (R) Paper Reading and Dicussion "Autoencoding Beyond Pixels Using a Learned Similarity Metric" Yi Homework 4 Due
Homework 5 Handout
Participation Questions Due at 11:59pm ET on Sunday
Week 14 Nov 23 (M) Ethical Issuses Joel Grus' Book, Chapter 26 Yi --
Nov 24 (T) Data Science Summary -- Yi Participation Questions Due at 11:59pm ET on Sunday
Nov 25-27 (W-F) Thanksgiving Holiday
Week 15 Nov 30 (M) Project Presentation I -- All --
Dec 1 (T) Project Presentation II -- All --
Dec 3 (R) Project Presentation III -- All Homework 5 Due
Participation Questions Due at 11:59pm ET on Sunday
Week 16 Dec 7 (M) Wrap-Up and Open Discussion -- Yi Technique Implementation Due
Dec 11 (T) Project Write-UPs (8 page conference formatted paper)

Academic Honesty

UGA Student Honor Code: “I will be academically honest in all of my academic work and will not tolerate academic dishonesty of others”. A Culture of Honesty, the University's policy and procedures for handling cases of suspected dishonesty, can be found at www.uga.edu/ovpi.

Mental Health and Wellness Resources

  • If you or someone you know needs assistance, you are encouraged to contact Student Care and Outreach in the Division of Student Affairs at 706-542-7774 or visit https://sco.uga.edu/. They will help you navigate any difficult circumstances you may be facing by connecting you with the appropriate resources or services.

  • UGA has several resources for a student seeking mental health services (https://www.uhs.uga.edu/bewelluga/bewelluga) or crisis support (https://www.uhs.uga.edu/info/emergencies).

  • If you need help managing stress anxiety, relationships, etc., please visit BeWellUGA (https://www.uhs.uga.edu/bewelluga/bewelluga) for a list of FREE workshops, classes, mentoring, and health coaching led by licensed clinicians and health educators in the University Health Center.

  • Additional resources can be accessed through the UGA App.

Disclaimer

The course syllabus is a general plan for the course; deviations announced to the class by the instructor may be necessary.