Class times: Thursday, 5:30 – 7:45pm, LL 311
Instructor: Prof. Daniel D. Leeds (my homepage)
Teaching assistant: Wanjia Song
Office: LL 610H for Office Hours; normally JMH 332 (Rose Hill)
E-mail:
Office hours: Instructor - Thursday 4-5pm; TA - Wednesday 2-3pm (TA Off Hr will be in LL 601)

Full syllabus

Course text: No book will be required, but the following will be useful as references.

• "Pattern Recognition and Machine Learning" by Bishop
• "Machine Learning: A Probabilistic Approach" by Murphy

• You can run Matlab in the computer lab or (without graphics) by remote login to our department machines.
• You can download your own student license for $50-$100.
• In Python, you can use numpy, scipy and matplotlib packages to write acceptable code for this class in Python. (You also may used the pandas package; you may not use packages like tensorflow for this class.)

1. Resources
2. Announcements
3. Slides
4. Assignments

Announcements:
Sept 3 11:50am: Dr Leeds will NOT be at office hours Sept 6. He will instead have office hours Tues Sept 4, 4-5pm in LL 610H; Wanjia's office hours will be Wednesday 2-3pm as normal. We WILL have lecture this Thursday, and HW 0 is due then!
Sep 18, 5:15pm: Prof Leeds is offline (inaccessible by e-mail) Tuesday afternoon until around 9pm Wednesday night. On Wed night, he'll answer any e-mails sent during that time; you are welcome to send questions to Wanjia during this offline time of mine too!
Sep 28, 12:05am: Midterm exam will be Oct 18.
Nov 16, 1:45am: For those who haven't submitted the written section of the homework: Wanjia will be on the sixth floor of LL between 2 and 5pm Friday to accept homeworks. If you can't find her, you can e-mail her. If this timing doesn't work for you, please e-mail your homework to me.
Nov 20, 2:40pm: Our final exam will be in class Dec 13, 5:30-7:30pm; it will be cumulative
Dec 10, 10:40pm: Dr Leeds will hold office hours both on Wednesday and Thursday this week, 4-5pm

Slides: Check slides after lectures as well for updates made during class!
I have not found any one textbook or online resource to be an optimal match for the material we cover at the mathematical level we cover it. However, Andrew Ng's lecture notes, available on Stanford's Machine Learning course web site, often can be a helpful online read. I recommend these notes as well as looking through one of our course textbooks.

	Supplementary reading
Lecture 1, Course logistics, background math, intro to classifiers. (Pre-recorded lecture PPT)
Lecture 1.5, Programming intro. (Pre-recorded lecture PPT)
Lecture 2, Bayes classifier. (Pre-recorded lecture PPT)	Ng notes 2 particularly pages 8-11
Lecture 3, Logistic classifier.	Ng Notes 1 Elements of Part II (starting on page 16)
Lecture 4, Support vector machines.	Ng notes 3 parts of pages 1-20
Lecture 5, Dimensionality reduction.	Ng notes 10 on PCA and Ng notes 11 on ICA
Lecture 6, Neural networks.	Chapter 1 and Chapter 2 of "Neural Networks and Deep Learning
Lecture 7, Hidden Markov Models.	Stanford notes
Lecture 8, Learning Theory.	Lecture Notes
Lecture 9, Convolutional Neural Nets.

Assignments:
Homework 0 - due Sep 6

HW 0 Answers

66.5-74 A range

59-66.5 B range

51-59 C range

41-51 D range

HW 1 Answers

44.5-49 A range written

35-44.5 B range written

28-35 C range written

---

30-34 A range code

24-30 B range code

18-24 C range code

12-18 D range code

HW 2 Answers

50-56 A range written

43-50 B range written

36-43 C range written

---

42-48 A range code

35-42 B range code

25-35 C range code

Midterm Answers

60-76 A range

45-60 B range

30-45 C range

Homework 3 answers

83.5-93.5 A range written

72-83.5 B range written

60.5-72 C range written

49-60.5 C range written

Due Nov 8: e-mail to Dr Leeds and Wanjia telling us:

List of group members

Data set you will use

If you plan to do your own optimizations/improvements, include a paragraph describing those optimizations/improvements