teaching

Course materials for the Interactive Audio Lab

View the Project on GitHub interactiveaudiolab/teaching

MACHINE LEARNING, Northwestern University EECS 349 Fall 2017

Top Calendar Links Slides Readings

Course Description

Machine Learning is the study of algorithms that improve automatically through experience. Topics covered typically include Bayesian learning, decision trees, Support Vector Machines, Reinforcement Learning, Markov models and neural networks.

Time & Place

Lecture: Monday, Wedensday 3:00PM - 4:20PM Tech L211

Recitation Fri 3:00PM - 3:50PM Tech L221 (Kim), Tech L251 (Pishdadian), Tech L168 (EECS Doctoral)

Instructors & Office Hours

Prof. Bryan Pardo Office Hours: Ford Building, Room 3-323, Mon 4:30 - 5:30pm

Bongjun Kim Office Hours: Ford Building, Room 3.317 (West Lounge), Tue 3:30pm-5:30pm

Fatemeh Pishdadian Office Hours: Ford Building, Room 3.317 (West Lounge), Fri 1:00 - 3:00pm

Policies

Grading: You can earn 110 points. Every test & assignment is worth 10 points. You’re graded on a basis of 100 points. In other words… 93-100 is an A, 90 - 92 is an A-, 87-89 is a B+, 83-86 is a B, 80-82 is a B-…and so on.

Extra Credit: The final homework is an extra credit assignment. No other extra credit will be assigned.

Late Policy: Assignments are due on Canvas by 11:59pm on the due date. Canvas is the only way assignments are accepted. Late assignments are docked 2 points per day, starting IMMEDIATELY. For example, an assignment handed in at 12:00am the next day has 2 points removed. An assignment that is 3 days late will have 6 points removed from the final grade.

Cheating & Academic Dishonesty: Do your own work. Academic dishonesty will be dealt with as laid out in the student handbook. Penalties include failing the class and can be more severe than that. If you have a question about whether something may be considered cheating, ask, prior to submitting your work.

Attendance is not graded.

Announcements and discussions will take place on the course Piazza page. You can sign up for the page here.

Course Calendar

Week Date Topic Assigned Due Points
1 Wed Sep 20 Decision Trees HW 1: Decision trees    
1 Fri Sep 22 Python 2.7      
2 Mon Sep 25 Measuring Distance      
2 Wed Sep 27 Nearest Neighbor Class      
2 Fri Sep 29 TBD HW 2: KNNs HW 1 10
3 Mon Oct 2 Linear regression      
3 Wed Oct 4 Linear discriminants      
3 Fri Oct 6 TBD HW 3: Regression HW 2 10
4 Mon Oct 9 Support Vector Machines      
4 Wed Oct 11 Support Vector Machines      
4 Fri Oct 13 Midterm preparation   HW 3 10
5 Mon Oct 16 MIDTERM   MIDTERM 10
5 Wed Oct 18 Collaborative Filtering      
5 Fri Oct 20 NO CLASS HW 4: Collaborative Filters    
6 Mon Oct 23 Naive Bayesian Classifiers      
6 Wed Oct 25 Experimental Validation      
6 Fri Oct 27 TBD HW 5: Naive Bayes HW 4 10
7 Mon Oct 30 Expectation Maximization      
7 Wed Nov 1 Gaussian Mixture Models      
7 Fri Nov 3 TBD HW 6: GMMs HW 5 10
8 Mon Nov 6 Reinforcement Learning      
8 Wed Nov 8 Reinforcement Learning      
8 Fri Nov 10 scikit-learn HW 7: RL HW 6 10
9 Mon Nov 13 Neural Networks      
9 Wed Nov 15 Neural Networks      
9 Fri Nov 17 tensorflow HW 8: Neural Networks HW 7 10
10 Mon Nov 20 Neural Networks      
10 Wed Nov 22 Neural Networks      
10 Fri Nov 24 NO CLASS HW 9: Extra Credit    
11 Mon Nov 27 Boosting   HW 8 10
11 Wed Nov 29 Active Learning      
11 Fri Dec 1 Final Preparation      
12 Mon Dec 4     HW 9 10
12 Fri Dec 8 Final exam (3-5pm)     10

Anaconda: The most popular python distro for machine learning

Scikit Learn: the most popular machine learning python package

Jupyter Notebook

Tensorflow: the most popular python DNN package

Keras: A nice python API for Tensorflow

My guide to installing Keras and Tensorflow on MacOS

Lecture Slides

first lecture

decision trees

working through an ID3 example

evaluating hypotheses

distance measures

nearest neighbors

linear regression

linear discriminants

support vector machines

collaborative filtering

probability & Bayes

Gaussian Mixture Models

Reinforcement Learning

Neural Networks

Boosting

Active Learning

Course Reading

Week 1: Decision Trees

Chapter 3 of Machine Learning

Week 2: Measuring Distance and KNN

The Wikipedia article on distance

Section 2.2.3 of An Introduction to Statistical Learning

The String-to-string Correction Problem

Week 3: Linear Regression & Linear Discriminants

Sections 3.1, 3.2, 4.2, 4.4 of An Introduction to Statistical Learning

Week 4: Support Vector Machines

A Tutorial on Support Vector Machines

Chapter 9 of An Introduction to Statistical Learning

Week 5: Collaborative Filtering

Chapter 2 of Recommender Systems: An Introduction

Week 6: Naive Bayesian Classifiers & Expectation Maximization

** STILL LOOKING FOR SOME GOOD READING ON NAIVE BAYES HERE ***

EM Demystified: An Expectation-Maximization Tutorial

Week 7: Gaussian Mixture Models & Markov Models

A Tutorial on Hidden Markov Models

Week 8: Reinforcement Learning

Chapters 3 and 6 of Reinforcement Learning: An Introduction

Weeks 9 and 10: Perceptrons and Multilayer Perceptrons

Chapter 1 of Parallel Distributed Processing

Chapter 4 of Machine Learning

Chapter 6 of Deep Learning

Blog: A hacker’s guide to neural nets

Week 11: Boosting

A Brief Introduction to Boosting

Improving Generalization with Active Learning

Top Calendar Links Slides Readings