|
COL774: Machine Learning
General Information
Semester: Sem II, 2019-20.
Instructor: Parag Singla (email: parags AT cse.iitd.ac.in)
Class Timings (Slot C):
- Tue, 8:00 am - 8:50am
- Wed, 8:00 am - 8:50am
- Fri, 8:00 am - 8:50am
Venue: LHC 316
TA Assignment Details
Sign up for Piazza
Code: As announced in class.
Announcements
[Aug 16, 2020]: Assignment 4 is out. Due Date: Saturday Sep 5, 2020, 11:50 pm.
[Mar 7, 2020]: Assignment 3 (part A) is out. Due Date (for both parts): Tuesday Mar 31, 2020, 11:50 pm.
[Mar 6, 2020]: Assignment 2: Updated Due Date: Sunday Mar 8, 11:50 pm.
[Feb 27, 2020]: Assignment 2 - Part B is out! Due Date (for both parts): Friday Mar 6, 11:50 pm.
[Feb 12, 2020]: Assignment 2 is out! Due Date: Wednesday Mar 4, 11:50 pm.
[Jan 21, 2020]: Assignment 1 is out! Due Date: Monday Feb 10, 11:50 pm.
[Dec 31, 2019]: Welcome! First Class: Today.
Course Objectives
(a) To familiarize with/develop the understanding of fundamental concepts of Machine
Learning (ML)
(b) To develop the understanding of working of a variety of ML algorithms (both
supervised as well as unsupervised)
(c) To learn to apply ML algorithms to real world
data/problems
(d) To update with some of the latest advances in the field
Course Content
NOTE: The exact list of topics below is tentative (until we are past that week).
We will update it as we go through the lectures in each week. So, stay tuned!
Week |
Topic |
Supplementary Notes |
Book Chapters |
1 | Introduction | | |
2,3 | Linear Regression (and Its Variants) |
lin-log-reg.pdf
| Bishop, Chapter 3.1 |
4 | Logistic Regression, Generalized Linear Models |
lin-log-reg.pdf
| Bishop, Chapter 3.1 |
5 | Gaussian Discriminant Analysis (GDA), Naive Bayes |
gda_nb.pdf |
Bishop, Chapter 4 |
6,7 | Support Vector Machines |
svm.pdf |
Bishop, Chapter 7.1 |
8 | Decision Trees, Random Forests |
dtrees.pdf
| Mitchell, Chapter 3.
Online Resource:
Random Forests |
9 | Neural Networks |
nnets.pdf
nnets-hw.pdf
|
Mitchell, Chapter 4 |
10 | Deep Learning |
deep_learning_slides.pdf
cnn.pdf
|
Online Resource:
Convolutional Neural Networks |
11 | K-Means, Gaussian Mixture Models |
kmeans.pdf
gmm.pdf
em.pdf
pca.pdf |
|
12 | Expectation Maximiation (EM), Principal Component Analysis (PCA) |
kmeans.pdf
gmm.pdf
em.pdf
pca.pdf |
|
13 | Learning Theory, Model Selection |
theory.pdf
model.pdf |
Mitchell, Chapter 7 |
14 | Advanced Topics |
|
|
dec31.pdf,
jan1.pdf,
jan3.pdf,
jan7.pdf,
jan8.pdf,
jan10.pdf
jan14.pdf
jan17.pdf
jan21.pdf
jan22.pdf
jan24.pdf
jan28.pdf
jan29.pdf
jan31.pdf
feb7.pdf
feb11.pdf
feb12.pdf
feb18.pdf
feb19.pdf
feb21.pdf
feb25.pdf
feb26.pdf
feb28.pdf
Class Notes (Date-Wise) for Recorded Lectures
Help Session Recordings
Pytorch Help Seesion (Aug 12) (approx size 350 MB)
Question-Answer Session Recordings
April 12 (Logistics, Neural Networks And Deep Learning):
apr12_video.mp4 (approx size 1.1 GB),
apr12_audio.m4a (approx size 46 MB)
April 19 (Logistics, K-Means, GMM, EM and Earlier):
apr19_video.mp4 (coming soon), apr19_audio.m4a (coming soon)
April 26 (Logistics, EM, PCA and Earlier):
apr26_video.mp4 (approx size 63 MB),
apr26_audio.m4a (approx size 15 MB)
May 3 (Logistics, PCA, Learning Theory and Earlier):
may3_video.mp4 (approx size 50 MB)
may3_audio.m4a (approx size 11 MB)
May 10 (Logistics, All Online Material):
Additional Resources
Review Material
References
- Machine Learning: A Probabilistic Perspective.
Kevin Murphy. MIT Press, 2012.
- Pattern Recognition and Machine Learning. Christopher Bishop. First Edition, Springer, 2006.
- Pattern Classification. Richard Duda, Peter Hart and David Stock. Second Edition, Wiley-Interscience, 2000.
- Machine Learning. Tom Mitchell. First Edition, McGraw-Hill, 1997.
Assignment Submission Instructions
- You are free to discuss the assignment problems with other students in the class. But all your code should be
produced independently without looking at/referring to anyone else's code.
- Python is the default programming
languages for the course. You should use it for programming your
assignments unless otherwise explicitly allowed.
- Code should be submitted using Moodle Page.
Make sure to include commenrs for readability.
- Create a separate directory
for each of the questions named by the question number. For instance, for question 1,
all your submissions files should be put in the directory named
Q1 (and so on for other questions). Put all the Question sub-directories in a single
top level directory. This directory should be named as "yourentrynumber_firstname_lastname".
For example, if your entry number is "2017anz7535" and your name is "Nitika Rao", your
submission directory should be named as "2017anz7535_nitika_rao". You should zip your
directory and name the resulting file as "yourentrynumber_firstname_lastname.zip" e.g. in
the above example it will be "2017anz7535_nitika_rao.zip". This single zip file should
be submitted online.
- Honor Code: Any cases of copying will be awarded a zero on the assignment and a
penalty of -10. More severe penalties may follow.
- Late Policy: You are allowed a total of 5 late days acorss all the assignments. You are
free to decide how you would like to use them. You will get a zero on an assignment once you exceed the
(total) allowed exemption of 5 days. This applies to the first 3 assignments in the course
(i.e., leaving out the last assigment based on a competition).
Practice Questions
Assignments
- Assignment 4 [Updated: Saturday Sep 5,2020]
Due Date: Saturday September 6, 2020. 11:50 pm
- Assignment 3 (Both Parts) [Updated: Sunday Apr 19,2020].
Datasets (Part B): alphabet.zip
Due Date for Part B: Friday April 24, 2020. 11:50 pm
- Assignment 3 (Part A)
Datasets (Part A): virus.zip
Due Date for Part A [Updated]: Friday Mar 27, 2020. 11:50 pm
- Assignment 2 (Part A),
Assignment 2 (Part B)
Datasets: fashion_mnist.zip (Part B)
Due Date (Updated on Mar 6): Sunday March 8, 2020. 11:50 pm
- Assignment 1 [Updated: Jan 29, 2020]
Datasets: ass1_data.zip
Due Date: Monday February 10, 2020. 11:50 pm
Grading Policy (Tentative)
Assignments | Ass 1: 7%, Ass 2: 8.5%, Ass 3: 8.5%, Ass 4: 10%. Total: 34% |
Minors | Minor 1: 17.5%, Minor 2: 17.5%. Total: 35%
| | [Minor 2 to be possibly held along with Major due to COVID].
| Major | 31% |
|