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 are available online via Canvas.

Week Date Topic Recitation Assignments Notes
Mon 08/26 HW 0 out (due on 09/06) [pdf] [tex]
Wed 08/28 Lecture #0: Introduction to CIS 419/519 [pptx] [pdf] [video] A Machine Learning Puzzle
Mon 09/02 Labor Day - No Class
1 Wed 09/04 Lecture #1: Introduction to Machine Learning [pptx] [pdf] [video] Sign up for Piazza Some Readings:
1. deep-learning-isnt-dangerous-magic-genie-just-math/
2. artificial-intelligence-challenges.html
3. Deep Learning: A Critical Appraisal
4. Roth-incidental-supervision.pdf
Thurs 09/05 Quiz 0 out (due Sun 09/08)
OPTIONAL
Fri 09/06 HW 0 due
2 Mon 09/09 Introduction to Python [GitHub] [video]
Tues 09/10 Course Selection Period Ends
Tues 09/10 Recitation #1
6:10pm DRLB A1 [colab]
Wed 09/11 Lecture #1: Introduction to Machine Learning [pptx] [pdf] [video] Recitation #1
4pm Towne 315 [colab]
Thurs 09/12 Quiz 1 out (due Sun 09/15) [pdf]
3 Mon 09/16 Lecture #1: Introduction to Machine Learning [pptx] [pdf] [video]
Tues 09/17 Recitation #2: Python Session 2
6:10pm DRLB A1 [slides]
Wed 09/18 Lecture #2: Decision Trees; Over-fitting [pptx] [pdf] [video] Recitation #2: Python Session 2
4pm Towne 315 [slides]
Efficient Learning of Linear Perceptrons
Thurs 09/19 Quiz 2 out (due Sun 09/22) [pdf]
4 Mon 09/23 Lecture #2: Decision Trees; Over-fitting [pptx] [pdf] [video] HW 1 out (due 10/07) HW files, t-table
Tues 09/24 Recitation #3
6:10pm DRLB A1 [pdf]
Wed 09/25 Lecture #3: Evaluation [pptx] [pdf] [video] Recitation #3
4pm Towne 315 [pdf]
Thurs 09/26 Quiz 3 out (due Sun 09/29) [pdf]
5 Mon 09/30 Lecture #4: On-line Learning, Perceptron, Kernels [pptx] [pdf] [video]
Tues 10/01 Recitation #4
6:10pm DRLB A1 [slides]
Wed 10/02 Lecture #4: On-line Learning, Perceptron, Kernels [pptx] [pdf] [video] Recitation #4
4pm Towne 315 [slides]
Thurs 10/03 Quiz 4 out (due Sun 10/06) [pdf]
6 Mon 10/07 Lecture #4: On-line Learning, Perceptron, Kernels [pptx] [pdf] [video] HW 2 out (due 10/21), HW2 Files Large Margins Using Perceptron
Mon 10/07 Drop Period Ends
Wed 10/09 Yom Kippur - No Class
Thurs 10/10 Quiz 5 out due (Sun 10/13)
7 Mon 10/14 Lecture #4: On-line Learning, Perceptron, Kernels [pptx] [pdf] [video]
Tues 10/15 Recitation #5
6:10pm DRLB A1 [pdf]
Wed 10/16 Lecture #5: Why Machine Learning Works: Explaining Generalization [pptx] [pdf] [video] Recitation #5
4pm Towne 315 [pdf]
Thurs 10/17 Quiz 6 out (due Sun 10/20) [pdf]
8 Mon 10/21 Lecture #5: Why Machine Learning Works: Explaining Generalization [pptx] [pdf] [video]
Tues 10/22 Midterm Review
6:10pm DRLB A1
Wed 10/23 Lecture #5: Why Machine Learning Works: Explaining Generalization [pptx] [pdf] [video] Midterm Review
4pm Towne 315
9 Mon 10/28 Midterm Exam Resources for midterm exam [CS446 Midterm Spring17], [CIS519 Midterm Spring18] [CIS519 Midterm Fall18] [CIS519 Midterm Fall19]
Wed 10/30 Lecture #6: Support Vector Machine [pptx] [pdf] [video]
Thurs 10/31 Quiz 7 out (due Sun 11/3)
10 Mon 11/04 Lecture #8: Neural Networks and Deep Learning [pptx] [video] [script] HW 3 out (due 11/18), HW3 Files
Mon 11/04 Last day to withdraw
Tues 11/05 Recitation #7
6:10pm DRLB A1 [pytorch guide]
Wed 11/06 Lecture #8: Neural Networks and Deep Learning [pptx] [video] [script] Recitation #7
4pm Towne 315 [pytorch guide]
Thurs 11/07 Quiz 8 out (due Sun 11/10)
11 Mon 11/11 Lecture #7: Boosting and Ensembles; Multi-class Classification and Ranking [pptx] [pdf] [video]
Tues 11/12 Recitation #8
6:10pm DRLB A1 [slides]
Wed 11/13 Lecture #9: Generative Models; Naive Bayes [pdf] [pptx] [video] Recitation #8
4pm Towne 315 [slides]
Thurs 11/14 Quiz 9 out (due Sun 11/17)
12 Mon 11/18 Lecture #9: Generative Models; Naive Bayes [pdf] [pptx] [video] HW 4 out (due 12/02), HW4 Files Was actually held on the morning of 11/20
Tues 11/19 Recitation #9
6:10pm DRLB A1 [slides]
Wed 11/20 Lecture #10: Un/Semi-Supervised Learning: EM and K-Means [pptx] [pdf] [video] Recitation #9
4pm Towne 315 [slides]
Thurs 11/21 Quiz 10 out (due Sun 11/24)
13 Mon 11/25 Lecture #10: Un/Semi-Supervised Learning: EM and K-Means [pptx] [pdf] [video]
Wed 11/27 Friday Schedule
11/28 - 11/29 Thanksgiving break
14 Mon 12/02 Lecture #11: Bayesian Networks [pptx] [pdf] [video] HW 5 out (due on 12/9, but you can turn it in on 12/11 without penalty) [tex]
Tues 12/03 Recitation #10
6:10pm DRLB A1 [slides]
Wed 12/04 Lecture #11: Bayesian Networks [pptx] [pdf] [video]

Recitation #10
4pm Towne 315 [slides]
Thurs 12/05 Quiz 11 out (due Sun 12/07)
15 Mon 12/09 Project Poster Session
16 Wed 12/18 Final Project Videos Due
Thurs 12/19 Final Exam
9:00am-11:00am
Skirkanich Auditorium/Towne 100
[CS446 Final 2012], [CS446 Final 2012 Solutions], [CS446 Final 2016], [CS446 Final 2016 Solutions]
Thurs 12/19 Final Project Reports Due