18-461/18-661: Intro to ML for Engineers

Instructors

Prof. Carlee Joe-Wong (cjoewong)
Prof. Gauri Joshi (gaurij)

TAs

Landelin Gihozo(lgihozo)
Neharika Jali(njali)
Jong-Ik Park(jongikp)
Arian Raje(araje)
Siddharth Shah(sgshah)
John Waithaka(jwaithak)
Steven Zeng(sczeng)

Lecture

PittsburghMon. and Wed.12:00 PM - 1:50 PM ETTEP3500
Silicon ValleyMon. and Wed.9:00 AM - 10:50 AM PTB23 118
RwandaMon. and Wed.7:00 PM - 8:50 PM CATCMR F205

Recitation

PittsburghFri.11:00 AM - 12:20 PM ETTEP3500
PittsburghFri.3:30 PM - 4:50 PM ETB235B
Silicon ValleyFri.12:30 PM - 1:50 PM PTB23 227
RwandaFri.6:00PM - 7:20PM CATCMR F205

Office Hours

See Piazza for the Office Hours Zoom links and locations.

Course Overview

This course provides an introduction to machine learning with a special focus on engineering applications. The course starts with a mathematical background required for machine learning and covers approaches for supervised learning (linear models, kernel methods, decision trees, neural networks) and unsupervised learning (clustering, dimensionality reduction), as well as theoretical foundations of machine learning (learning theory, optimization). Evaluation will consist of mathematical problem sets and programming projects targeting real-world engineering applications.

Prerequisites

This course is intended for graduate students and qualified undergraduate students with a strong mathematical and programming background. Undergraduate level training or coursework in algorithms, linear algebra, calculus, probability, and statistics is suggested. A background in programming will also be necessary for the problem sets; students are expected to be familiar with python or learn it during the course. At CMU, this course is most similar to MLD's 10-601 or 10-701, though this course is meant specifically for students in engineering.

Textbooks

There will be no required textbooks, though we suggest the following to help you to study (all available online): We will provide suggested readings from these books in the schedule below.

Piazza

We will use Piazza for class discussions. Please go to the course Piazza site to join the course forum (note: you must use a cmu.edu email account to join the forum). We strongly encourage students to post on this forum rather than emailing the course staff directly (this will be more efficient for both students and staff). Students should use Piazza to:

The course Academic Integrity Policy must be followed on the message boards at all times. Do not post or request homework solutions! Also, please be polite.

Grading Policy

Grades will be based on the following components:

Gradescope: We will use Gradescope to collect PDF submissions of each problem set. Upon uploading your PDF, Gradescope will ask you to identify which page(s) contains your solution for each problem - this is a great way to double check that you haven't left anything out. The course staff will manually grade your submission, and you'll receive feedback explaining your final marks.

Regrade Requests: If you believe an error was made during grading, you'll be able to submit a regrade request on Gradescope. For each homework, regrade requests will be open for only 1 week after the grades have been published. This is to encourage you to check the feedback you've received early!

Academic Integrity Policy

Group studying and collaborating on problem sets are encouraged, as working together is a great way to understand new material. Students are free to discuss the homework problems with anyone under the following conditions: Students are encouraged to read CMU's Academic Integrity Policy.

Acknowledgments

This course is based in part on material developed by Fei Sha, Ameet Talwalkar, Matt Gormley, and Emily Fox. We also thank Anit Sahu and Joao Saude for their help with course development.


Schedule (Subject to Change)

DateTopicsReadingHW
1/13 Introduction and Probability Review [Slides] [Annotated] KM, Ch. 1
1/15 MLE/MAP and Linear Algebra Review [Slides] [Annotated] TM, Estimating Probabilities
KM, Ch. 2 (for a refresh in probability)
Math4ML (review/refresher)
Vectors, Matrices, and Least Squares
Matrix Cookbook
1/17 Recitation [Slides] HW 1 Release
1/20 MLK Day - No Class
1/22 Linear Regression, Part I [Slides] KM, Ch. 7.1-7.3
Deep Learning Book, Ch. 5*
1/25 Recitation
1/27 Linear Regression, Part II KM, Ch. 7.4-7.6
Intro to regression
1/29 Overfitting, Bias/variance Trade-off, Evaluation Deep Learning, Ch. 5.2-5.4
KM, Ch. 6.4
1/31 Recitation HW 1 Due
HW 2 Release
2/03 Naive Bayes CIML, Ch. 9
KM, Ch. 3.5
2/05 Logistic Regression KM, Ch. 8.1-8.4, 8.6
Discriminative vs. Generative
2/07 Recitation
2/10 Mini-exam 1 and Multi-class Classification KM, Ch. 8.5
2/12 SVM, Part I ESL, Ch. 12
KM Ch. 14.5
2/14 Recitation
2/17 SVM, Part II Idiot's Guide to SVM
Duality Supplement
2/19 Nearest Neighbors CIML, Ch. 3.1-3.2
2/21 Recitation HW 2 Due
HW 3 Release
2/24 Decision Trees CIML, Ch. 1.3
KM, Ch. 16.2
ESL, Ch. 9.2
2/26 In-class Midterm Exam
3/03-3/05 Spring Break - No Classes
3/10 Boosting, random forests ESL, Ch. 10.1, 10.4-10.6
3/12 Neural Networks, Part I Learning Deep Architectures for AI
ImageNet
3/14 Recitation
3/17 Neural Networks, Part II Neural Networks and Deep Learning, Ch.3
Regularization for Deep Learning
3/19 Neural Networks, Part III Neural Networks and Deep Learning, Ch.3
Regularization for Deep Learning
3/21 Recitation
3/24 PyTorch
3/26 Mini-exam 2 and Neural Networks Part III.5
3/28 Recitation HW 3 Due
HW 4 Release
3/31 Distributed Learning
4/02 Clustering, Part I CIML, Ch. 15.1
4/04 Recitation
4/07 Clustering, Part II ESL, Ch. 14.3.1-14.3.9
4/09 Dimensionality Reduction PCA
Independent Component Analysis
4/11 Recitation
4/14 Online Learning (Bandits)
4/16 Mini-exam 3 and Guest lecture HW 4 due
HW 5 Release
4/21 Reinforcement Learning, Part I
4/23 Reinforcement Learning, Part II and Course Review
4/25 Recitation
4/28-5/02 Final Exams Week HW5 due