Schedule

This is a tentative syllabus and schedule. Topics, reading assignments, due dates, and exam dates are subject to change. All assignments and projects are due by 11:59:59pm Eastern time on the day listed.

The readings will come from Machine Learning (Flach), Learning from Data (LfD), the reading packet (Handout), or online sources.

Recordings of the lectures will be available online via Youtube.

We will make the 2019 slides available as a preview, and update them with our 2020 slides as we move through the course.

Week Date Topic Recitation Assignments Notes
0 Wed 09/02 Lecture #0: Introduction to CIS 419/519 [pptx] [pdf] [video] HW 0 out [pdf] [tex] (due on 09/14) A Machine Learning Puzzle
1 Mon 09/07 No Class - Labor Day
Tues 09/08 Recitation: Python Tutorial [Google Doc] [Github]
Wed 09/09 Lecture #1: Introduction to Machine Learning [pptx] [pdf] [video] Recitation: Python Tutorial [Google Doc] [Github] Join Piazza Some Readings:
1. Deep Learning Isn't Dangerous
2. AI challenges
3. Deep Learning: A Critical Appraisal
4. Roth Incidental Supervision
Thurs 09/10 Quiz 0 out (due Sun 09/13)
OPTIONAL
2 Mon 09/14 Lecture #1: Introduction to Machine Learning [pptx] [pdf] [video] HW 0 due
Tues 09/15 Course Selection Period Ends
Recitation #1 (Details TBD)
Wed 09/16 Lecture #1: Introduction to Machine Learning [pptx] [pdf] [video] Recitation #1 (Details TBD)
Thurs 09/17 Quiz 1 out (due Sun 09/20)
3 Mon 09/21 Lecture #2: Decision Trees; Over-fitting [pptx] [pdf] [video] HW 1 out [pdf] [materials](due on 10/05) Efficient Learning of Linear Perceptrons
Tues 09/22 Recitation #2 [pdf]
Wed 09/23 Lecture #2: Decision Trees; Over-fitting [pptx] [pdf] [video] Recitation #2 [pdf]
Thurs 09/24 Quiz 2 out (due Sun 09/27)
4 Mon 09/28 Yom Kippur - No Class
Tues 09/29 Recitation #3 [pdf]
Wed 09/30 Lecture #3: Evaluation [pptx] [pdf] [video] Recitation #3 [pdf]
Thurs 10/01 Quiz 3 out (due Sun 10/04)
5 Mon 10/05 Lecture #4: On-line Learning, Perceptron, Kernels [pptx] [pdf] [video] HW 1 due

HW 2 out [pdf] [materials](due 10/22)
Lecture Notes: On-line Learning

Google Colab: Online Learning
Tues 10/06 Recitation #4 [pdf]
Wed 10/07 Lecture #4: On-line Learning, Perceptron, Kernels [pptx] [pdf] [video] Recitation #4 [pdf]
Thurs 10/08 Quiz 4 out (due Sun 10/11)
6 Mon 10/12 Lecture #4: On-line Learning, Perceptron, Kernels [pptx] [pdf] [video] Large Margins Using Perceptron
Drop Period Ends
Tues 10/13 Recitation #5 [pdf]
Wed 10/14 Class Canceled (piazza@257 for details) Recitation #5 [pdf]
Thurs 10/15 Quiz 5 out (due Sun 10/18)
7 Mon 10/19 Lecture #4: On-line Learning, Perceptron, Kernels [pptx] [pdf] [video] Google Colab: Online Learning 2
Tues 10/20 Recitation #6 (Details TBD)
Wed 10/21 Lecture #5: Why Machine Learning Works: Explaining Generalization [pptx] [pdf] [video] Recitation #6 (Details TBD) Lecture Notes: ML Generalization

PAC Learning (ipynb)
Thurs 10/22 HW 2 due

Quiz 6 out (due Sun 10/25)
8 Mon 10/26 Lecture #5: Why Machine Learning Works: Explaining Generalization [pptx] [pdf] [video]
Tues 10/27 Midterm Review
Wed 10/28 Midterm Exam [CS446 Midterm Spring17], [CIS519 Midterm Spring18] [CIS519 Midterm Fall18] [CIS519 Midterm Fall19]
9 Mon 11/02 Lecture #5: Why Machine Learning Works: Explaining Generalization [pptx] [pdf] [video] HW 3 out [pdf] [materials](due 11/16)
Wed 11/04 Lecture #6: Support Vector Machine [pptx] [pdf] [video]
Thurs 11/05 Quiz 7 out (due Sun 11/08)
10 Mon 11/09 Lecture #7: Boosting and Ensembles; Multi-class Classification and Ranking [pptx] [pdf] [video]
Last day to withdraw
Tues 11/10 Recitation #7 [pdf]
Wed 11/11 Lecture #7: Boosting and Ensembles; Multi-class Classification and Ranking [pptx] [pdf] [video] Recitation #7 [pdf]
Thurs 11/12 Quiz 8 out (due Sun 11/15)
11 Mon 11/16 Lecture #8: Neural Networks and Deep Learning [pptx] [pdf] [video] HW 3 Due

HW 4 out [pdf] [colab] [materials] (due 12/07)
Tues 11/17 Recitation #8 [pdf] [colab]
Wed 11/18 Lecture #8: Neural Networks and Deep Learning [pptx] [pdf] [video] Recitation #8 [pdf] [colab]
Thurs 11/19 Quiz 9 out (due Sun 11/22)
12 Mon 11/23 Lecture #9: Generative Models; Naive Bayes [pdf] [pptx] [video] Naive Bayes Worksheet (ipynb)
Tues 11/24 Recitation [pdf]
Wed 11/25 No Class Friday Schedule
11/26 - 11/29 Thanksgiving break
13 Mon 11/30 Lecture #9: Generative Models; Naive Bayes [pdf] [pptx] [video]
Tues 12/01 Recitation #9 (Details TBD)
Wed 12/02 Lecture #10: Un/Semi-Supervised Learning: EM and K-Means [pptx] [pdf] [video] Recitation #9 (Details TBD) HW 5 out (due 12/15 - hard deadline, no late days allowed) [pdf] [latex] EM Worksheet (ipynb)
Thurs 12/03 Quiz 10 out (due Sun 12/06)
14 Mon 12/07 Lecture #10: Un/Semi-Supervised Learning: EM and K-Means [pptx] [pdf] [video] HW 4 due
Tues 12/08 Recitation #10 (Details TBD)
Wed 12/09 Lecture #11: Bayesian Networks [pptx] [pdf] [video] Recitation #10 (Details TBD)
Thurs 12/10 Lecture #11: Bayesian Networks [pptx] [pdf] [video] HW 5 Due

Quiz 11 out (due Sun 12/13)
Monday Schedule
Finals Friday 12/18 Final Exam Exam Prep to be posted [CS446 Final 2012], [CS446 Final 2012 Solutions], [CS446 Final 2016], [CS446 Final 2016 Solutions]
Monday 12/21 Final Project Reports and Video Due