~~SITETITLE~~

Jordan Boyd-Graber
4146 Iribe
jbg@boydgraber.org

Data Science

Logistics

Location	Virtual, with potential on-campus meetings if Covid situation improves
Time	Mondays 9:30 AM on Zoom
Mailing List	https://piazza.com/umd/fall2020/inst808/home
Suggested Text	Natural Language Processing with PyTorch
Homework Template	https://github.com/ezubaric/methods-hw
Syllabus	https://docs.google.com/document/d/13jRziPi2jWEmS19Ll8rfD1Y7heztukb3uxM9sj-cr8E/edit?usp=sharing
Homework Turn-in	https://umd.instructure.com/courses/1288606

People

Professor

Jordan Boyd-Graber

Schedule

How to read this table:

1. Do the reading under the corresponding date.
2. Homeworks are due at 11:55 PM (Eastern) the day listed on the schedule.

Date	Topic	Assignment Due	Materials
Mon 31. Aug	Course Introduction, Python Review, Math Review
	Videos: What is this class? How to take a class with me Why Python, Introduction Classes File IO, Complete Example Resources: Python Tutorial List of Python Resources
Mon 14. Sept	Math Review: Distributions, Statistics, Vectors, Matrices, Derivative and Optimization		[Slides]
	Videos: Functions Distributions Vectors Matrix math Gradients and Optimization Reading: Matrix Math Textbook Basic Probability and Statistics Textbook Calculus Videos
Mon 21. Sept	Representations		[In-Class Exercise]
	Reading: First half of Chapter 1 Videos: Introduction to Representations Information Retrieval tf-idf Distributed Representations Understanding Word2Vec
Wed 23. Sep	Homework 0 Due: Python / Math Warmup	[Github]
Mon 28. Sept	Hypothesis Testing		[Slides Example]
	Videos: Basics Confidence Intervals Discrete Tests Continuous Tests Reading: Parameter Estimation More Advanced Prob+Stats Textbook that also Covers Statistical Tests
Mon 5. Oct	Linear and Logistic Regression		[Slides Ex]
	Reading: Chapter 5 of SLP Notes from Andrew Ng (Optional) Videos: Linear regression Logistic regression for classification SGD for logistic regression
Mon 12. Oct	Introducing Deep Learning and PyTorch		[Example]
	Reading: Second Half of Chapter 1 Videos: Deep Learning Intro Backprop Frameworks Pytorch Deep Averaging Networks
Wed 14. Oct	Homework 1 Due: Logistic Regression	[Github]
Mon 19. Oct	Clustering and Topic Models: Intro		[Slides] [In-class Discussion]
	Readings: Chapter 1 of "Applications of Topic Models" Videos: Clustering and k-Means (Old video, sorry!) Topic Models Intro Evaluating Topic Models Gibbs Sampling
Mon 26. Oct	PyTorch Nuts and Bolts
	Readings: Chapter 4 Videos: (Not by me, this time) Logistic Regression Batching Softmax Saving and Loading Models
Wed 28. Oct	Homework 3 Due: Project Proposal	[Github]
Mon 2. Nov	Sequence Models		[Slides] [In-class Discussion]
	Readings: Chapters 6-7 Required Videos: Part of Speech Tagging, HMMs RNNs LSTM
Mon 9. Nov	Exam
Wed 11. Nov	Homework 2 Due: Logistic Regression Redux	[Github]
Mon 16. Nov	Machine Translation, Sequence to Sequence		[LSTM Example] [In-class Discussion]
	Videos: LSTM (if you didn't watch last time) Word-based translation Phrase translation Sequence to sequence
Mon 23. Nov	Visualization		[Slides] [In-class Discussion]
	Reading: Part 1 Part 2 Videos: Introducing Plotnine Napoleon in Russia How not to visualize something
Mon 30. Nov	Language Models: Classical to Neural		[Slides] [In-class Discussion]
	Reading: What we know about how BERT works Videos: Language models Backoff and smoothing Neural language models
Mon 7. Dec	Project Presentations
Thu 17. Dec	Project Writeups Due	[Github]

Page by Jordan Boyd-Graber. Last modified: ~~TIMESTAMP~~