CSE/STAT 416

Welcome to CSE/STAT 416: Introduction to Machine Learning! 🎉

Registration

Do not email the course staff or instructor requesting an add-code for the course. The course staff do not have any add-codes. Please see the Registration FAQ for answers to common registration questions.

Announcements¶

Jun 17

Welcome to CSE/STAT 416 🎉

Information about the class posted including:

Links to the course website (here) and other resources
Information about the class structure. No pre-class work for the first class.
Office hours start Monday, June 24^th.

See the full announcement on Ed!

This Week (at a glance)¶

Monday (07/15)

MIDTERM OPEN @ 8:30AM

Wednesday (07/17)

MIDTERM DUE @ 11:59PM

Thursday (07/18)

Attend Section (plz 🥹)!

Calendar¶

Info

This is a rough sketch of the quarter and things are subject to change. We can accurately predict the past, but predicting the future is hard!

Lessons

Anything listed in the “Lesson” materials for a day should be done before attending class that day. We recommend doing all the slides before the “Pause and Think” slide. Each class session will start by reviewing what was in the Lesson and then most time will be spent on working on practice problems in the Lessons. See the syllabus for more info!

	Topic	Homeworks	Learning Reflections
Module 0 - Introduction / Regression
Mon 06/17	LES 00 Regression Note: Normally there is are pre-class materials that you should complete before attending class. For the first day there are none! You should complete the Checkpoint after class (due before the next class). Note (2): The CSE/STAT 416 Training links for today are extremely useful resources to make sure you are prepared for the class. The course will be in Python, so Resources 1 and 2 will be very helpful if you are less familiar with the language. Resource 3 covers the mathematical background we expect students to be comfortable with in the course. You are expected to complete these trainings, but they are not factored into your grade. We encourage you to work on them now before assignments are released. pre-class: lesson megathread in-class: pdf annotated pptx post-class: checkpoint resources: videos extra resources Videos Recording Extra resources [Schafer] AnIML - Introduction (draft) Note: This is a draft book for the course. It is still a work in progress so it will still have some errors and TODOs left throughout. Feedback is welcome and encouraged! [Schafer] AnIML - Linear Regression (draft) [Nguyen] Previous Quarter Lecture Notes Note: These notes are from a different offering of the course and may use slightly different notation and terminology. [ESL] Section 1, 2.3.1 Note: The Elements of Statistical Learning [ESL] is an advanced machine learning textbook that we link to as optional readings for students who want to learn more of the nitty-gritty details behind the model's derivations. You do not need to understand readings labeled as "Optional" CSE/STAT 416 Training: 1) Python Practice, 2) numpy Practice, 3) Math/Probability/Statistics Practice
Mon 06/17		Out HW0 House Prices Due 11:59 pm	Out LR0 Due 11:59 pm
Tue 06/18
Tue 06/18
Wed 06/19	Holiday: Juneteenth
Wed 06/19	Holiday: Juneteenth
Thu 06/20	SEC 00 Course Infrastructure; Pandas resources: handout videos Videos Recording
Thu 06/20
Fri 06/21
Fri 06/21
Module 1 - Assessing Performance
Mon 06/24	LES 01 Assessing Performance; Bias + Variance Tradeoff pre-class: lesson megathread in-class: pdf annotated pptx demo post-class: checkpoint resources: videos extra resources advanced resources Videos Recording Extra resources [Schafer] AnIML - Assessing Performance (draft) [Nguyen] Lecture Notes from previous quarter Advanced resources [ESL] Section 2.3.1, 7.1-7.4
Mon 06/24			Out LR1 Due 11:59 pm
Tue 06/25
Tue 06/25
Wed 06/26	LES 02 Regularization: Ridge pre-class: lesson megathread in-class: pdf annotated pptx demo post-class: checkpoint resources: videos extra resources advanced resources Videos Recording Extra resources [Schafer] AnIML - Ridge Regression (draft) [Nguyen] Lecture Notes from previous quarter Advanced resources [ESL] Section 3.1-3.2, 3.4.1 [ESL] Section 7.1-7.4
Wed 06/26		Out HW1 Ridge and LASSO Due 11:59 pm
Thu 06/27	SEC 01 Ridge and LASSO; Code resources: handout videos Videos Recording
Thu 06/27
Fri 06/28
Fri 06/28
Module 2 - Classification
Mon 07/01	LES 03 Regularization: LASSO, Feature selection. Classification Introduction pre-class: lesson megathread in-class: pdf annotated pptx demo post-class: checkpoint resources: videos extra resources advanced resources Videos Recording Extra resources [Nguyen] Lecture notes from previous quarter [Schafer] AnIML - LASSO and Feature Selection Advanced resources [ESL] Section 2.9, 5.5.2, 7.2 [ESL] Section 3.4.2, 7.10
Mon 07/01			Out LR2 Due 11:59 pm
Tue 07/02
Tue 07/02
Wed 07/03	LES 04 Classification / MLE / Logistic Regression pre-class: lesson megathread in-class: pdf annotated pptx demo post-class: checkpoint resources: videos extra resources advanced resources Videos Recording Extra resources [Nguyen] Lecture notes from previous quarter [Schafer] AnIML - Classification Advanced resources [ESL] Section 1, 2.3.1, 4.1-4.2
Wed 07/03		Out HW2 Sentiment Analysis with Logistic Regression Due 11:59 pm
Thu 07/04	SEC 02 Classification ; Logistic Regression resources: handout videos Videos Recording
Thu 07/04
Fri 07/05
Fri 07/05
Module 3 - Societal Impact, Bias, and Fairness
Mon 07/08	LES 05 Bias and Fairness, Tradeoffs pre-class: lesson megathread in-class: pdf annotated pptx post-class: checkpoint resources: videos extra resources advanced resources Videos Recording Extra resources [Schafer] AnIML - Bias and Fairness (7.1-7.3) Advanced resources People and AI Research (PAIR, Google) ACM Conference on Fairness, Accountability, and Transparency (ACM FAccT) A Framework for Understanding Sources of Harm throughout the Machine Learning Life Cycle (Suresh & Guttag 2019)
Mon 07/08			Out LR3 Due 11:59 pm
Tue 07/09
Tue 07/09
Wed 07/10	LES 06 Naive Bayes / Decision Trees pre-class: lesson megathread in-class: pdf annotated pptx post-class: checkpoint resources: videos extra resources Videos Recording Extra resources [Schafer] AnIML - Naïve Bayes [Schafer] AnIML - Decision Trees [Nguyen] Lecture notes from a previous quarter
Wed 07/10		Out HW3 Loan Safety with Decision Trees Due 11:59 pm
Thu 07/11	SEC 03 Trees and Ensemble Methods + Midterm Review resources: Tree/Ensemble Handout Midterm Handout videos Videos Trees and Ensemble Methods Recording Midterm Review Recording
Thu 07/11
Fri 07/12
Fri 07/12
Module 4 - Trees/Ensemble Methods
Mon 07/15	LES 07 Ensemble Methods pre-class: lesson megathread in-class: pdf annotated pptx post-class: checkpoint resources: videos extra resources advanced resources Videos Recording Extra resources [Schafer] AnIML - Ensemble Methods (coming soon) [Nguyen] Lecture notes from a previous quarter Advanced resources Deriving AdaBoost Explaining AdaBoost (Schapire 2013) [ESL] Section 9.2.4, 10.1-10.10
Mon 07/15		Out EXAM Midterm Due 11:59 pm	Out LR4 Due 11:59 pm
Tue 07/16		Out EXAM Midterm Due 11:59 pm
Tue 07/16
Wed 07/17	LES 08 Neural Networks pre-class: lesson megathread in-class: pdf annotated pptx post-class: checkpoint resources: videos extra resources advanced resources Videos Recording Extra resources [Schafer] AnIML - Neural Networks (coming soon) [Nguyen] Lecture notes from a previous quarter Playground Advanced resources Neural Network Notes Backpropogation Algorithm Proof of Approximating and Function
Wed 07/17		Out HW4 Deep Learning with PyTorch Due 11:59 pm
Thu 07/18	SEC 04 Deep Learning resources: handout
Thu 07/18	SEC 04 Deep Learning resources: handout
Fri 07/19
Fri 07/19
Module 5 - Deep Learning
Mon 07/22	LES 09 Deep Learning; Convolutional Neural Networks pre-class: lesson megathread in-class: pdf annotated pptx post-class: checkpoint resources: videos extra resources
Mon 07/22			Out LR5 Due 11:59 pm
Tue 07/23
Tue 07/23
Wed 07/24	LES 10 Precision + Recall / kNN pre-class: lesson megathread in-class: pdf annotated pptx post-class: checkpoint resources: videos extra resources
Wed 07/24		Out HW5 ML Practice on Kaggle Due 11:59 pm
Thu 07/25	SEC 05 Kaggle Setup resources: handout
Thu 07/25	SEC 05 Kaggle Setup resources: handout
Fri 07/26
Fri 07/26
Module 6 - Non-Parametric Methods
Mon 07/29	LES 11 Kernel Methods; Locality Sensitive Hashing pre-class: lesson megathread in-class: pdf annotated pptx post-class: checkpoint resources: videos extra resources
Mon 07/29			Out LR6 Due 11:59 pm
Tue 07/30
Tue 07/30
Wed 07/31	LES 12 Clustering pre-class: lesson megathread in-class: pdf annotated pptx post-class: checkpoint resources: videos extra resources
Wed 07/31		Out HW6 k-means with Text Data Due 11:59 pm
Thu 08/01	SEC 06 Numpy ; Variable Encoding ; Clustering resources: handout
Thu 08/01
Fri 08/02
Fri 08/02
Module 7 - Clustering
Mon 08/05	LES 13 Hierarchical Clustering pre-class: lesson megathread in-class: pdf annotated pptx post-class: checkpoint resources: videos extra resources
Mon 08/05			Out LR7 Due 11:59 pm
Tue 08/06
Tue 08/06
Wed 08/07	LES 14 PCA / Recommender Systems Intro pre-class: lesson megathread in-class: pdf annotated pptx post-class: checkpoint resources: videos extra resources
Wed 08/07		Out HW7 Tweet Topic Modelling Due 11:59 pm
Thu 08/08	SEC 07 PCA ; Recommender Systems resources: handout
Thu 08/08	SEC 07 PCA ; Recommender Systems resources: handout
Fri 08/09
Fri 08/09
Module 8 - Recommender Systems
Mon 08/12	LES 15 Recommender Systems / Matrix Factorization pre-class: lesson megathread in-class: pdf annotated pptx post-class: checkpoint resources: videos extra resources
Mon 08/12			Out LR8 Due 11:59 pm
Tue 08/13
Tue 08/13
Wed 08/14	LES 16 Course Wrap Up; Next Steps; Generative AI pre-class: lesson megathread in-class: pdf annotated pptx post-class: checkpoint resources: videos extra resources
Wed 08/14
Thu 08/15	SEC 08 Final Review resources: handout
Thu 08/15	SEC 08 Final Review resources: handout
Fri 08/16
Fri 08/16
Module 9 - Course Wrap Up
Mon 08/19	LES 17 Final Exam pre-class: lesson megathread in-class: pdf annotated pptx post-class: checkpoint resources: videos extra resources
Mon 08/19
Tue 08/20
Tue 08/20
Wed 08/21
Wed 08/21