10-301 + 10-601, Spring 2020

Important Notes

This schedule is tentative and subject to change. Please check back often.

Lecture Videos

We have included links to individual videos on the schedule below.
You can also view all the videos in the Panopto folder: [Andrew ID Required] https://scs.hosted.panopto.com/Panopto/Pages/Sessions/List.aspx?folderID=5ab64853-25e2-49bc-a9ec-ab3b0144c203
The above folder contains all the lecture video recordings. To access them, please select Sign in using "Canvas".

Lecture Polls

This is a permanent link to the current / next poll

Tentative Schedule

Date	Lecture	Readings	Announcements
Classification & Regression
Mon, 13-Jan	Lecture 1 : Course Overview [Slides] [Whiteboard] [Video]	10601 Notation Crib Sheet. Matt Gormley (2018). Command Line and File I/O Tutorial. 10601 Course Staff (2020). 10601 Learning Objectives. Matt Gormley (2018). Visual Information Theory. Christopher Olah (2015). blog.
Wed, 15-Jan	Lecture 2 : Decision Trees [Slides] [Whiteboard] [Video]	Decision Trees. Hal Daumé III (2017). CIML, Chapter 1.	HW1 out
Fri, 17-Jan	Recitation: HW1 [Video]
Mon, 20-Jan	(No Class: Martin Luther King Day)
Wed, 22-Jan	Lecture 3 : Decision Trees [Slides] [Whiteboard] [Video] [Poll]	Limits of Learning. Hal Daumé III (2017). CIML, Chapter 2.	HW1 due HW2 out (Thu)
Fri, 24-Jan	Recitation: HW2 [Video]
Mon, 27-Jan	Lecture 4 : k-Nearest Neighbors [Slides] [Whiteboard] [Video] [Poll]	Geometry and Nearest Neighbors. Hal Daumé III (2017). CIML, Chapter 3.
Wed, 29-Jan	Lecture 5 : Model Selection [Slides] [Whiteboard] [Video] [Poll]
Fri, 31-Jan	Recitation: Colab / Linear Algebra Libraries / Debugging [Video]
Mon, 3-Feb	Lecture 6 : Perceptron [Slides] [Whiteboard] [Video] [Poll]	The Perceptron. Hal Daumé III (2017). CIML, Chapter 4.
Linear Models
Wed, 5-Feb	Lecture 7 : Linear Regression [Slides] [Whiteboard] [Video] [Poll]	Linear Regression. Kevin P. Murphy (2014). Machine Learning: A Probabilistic Perspective. Chapter 7.1-7.3.	HW2 due HW3 out (Thu)
Fri, 7-Feb	Lecture 8 : Optimization for ML [Slides] [Whiteboard] [Video] [Poll]	Optimization lecture notes from 10-600. Geoff Gordon (2016).	HW1 Solution Session (Thu or Fri)
Mon, 10-Feb	Recitation: HW3 [Video]
Wed, 12-Feb	Lecture 9 : Midterm Exam Review / Binary Logistic Regression [Slides] [Whiteboard] [Video] [Poll]	Estimating Probabilities: MLE and MAP. Tom Mitchell (2016, draft). Logistic Regression. Kevin P. Murphy (2014). Machine Learning: A Probabilistic Perspective. Chapter 1.4.6, 8.1-8.3, 8.6.	Exam 1 practice problems out HW2 Solution Session
Fri, 14-Feb	(No recitation)		HW3 due
Mon, 17-Feb	Lecture 10 : Multinomial Logistic Regression [Slides] [Whiteboard] [Video] [Poll]		HW3 Solution Session
Tue, 18-Feb	Midterm Exam 1 (7:00PM - 9:00PM) -- details will be announced on Piazza
Wed, 19-Feb	Lecture 11 : Feature Engineering / Regularization [Slides] [Whiteboard] [Video] [Poll]	Regularization for Deep Learning. Ian Goodfellow, Yoshua Bengio, & Aaron Courville (2016). Deep Learning, Chapter 7.1 and 7.8.	HW4 out
Fri, 21-Feb	Recitation: HW4 [Video]
Deep Learning
Mon, 24-Feb	Lecture 12 : Neural Networks [Slides] [Whiteboard] [Video] [Poll]	Deep Feedforward Networks. Ian Goodfellow and Yoshua Bengio and Aaron Courville (2016). Deep Learning, Chapter 6.1-6.4.
Wed, 26-Feb	Lecture 13 : Backpropagation [Slides] [Whiteboard] [Video] [Poll]	Deep Feedforward Networks. Ian Goodfellow, Yoshua Bengio, & Aaron Courville (2016). Deep Learning, Chapter 6.5.
Fri, 28-Feb	Lecture 14 : Deep Learning [Slides] [Whiteboard] [Video] [Poll]	[Optional] Deep learning. Yann LeCun, Yoshua Bengio, & Geoffrey Hinton (2015). Nature.	HW4 due HW5 out
Mon, 2-Mar	Recitation: HW5 [Video]
Learning Theory
Wed, 4-Mar	Lecture 15 : Learning Theory: PAC Learning [Slides] [Whiteboard] [Video] [Poll]	Generalization Abilities: Sample Complexity Results.. Nina Balcan (2015). Lecture notes.	HW4 Solution Session
Fri, 6-Mar	(No class: Mid-semester break)
Mon, 9-Mar	(No class: Spring break)
Wed, 11-Mar	(No class: Spring break)
Fri, 13-Mar	(No class: Spring break)
Mon, 16-Mar	(No class: All classes cancelled)
Wed, 18-Mar	Lecture 16 : Learning Theory: PAC Learning [Slides] [Whiteboard] [Video] [Poll]	A Few Useful Things to Know about Machine Learning. Pedro Domingos (2012).
Generative Models
Fri, 20-Mar	Lecture 17 : MLE/MAP [Slides] [Whiteboard] [Video] [Poll]	Estimating Probabilities: MLE and MAP. Tom Mitchell (2016, draft).	HW5 due (Sun, Mar-22) HW6 out
Mon, 23-Mar	Lecture 18 : Naive Bayes [Slides] [Whiteboard] [Video] [Poll]	Generative and Discriminative Classifiers: Naive Bayes and Logistic Regression. Tom Mitchell (2016, draft).
Wed, 25-Mar	Recitation: HW6 [Video]
Graphical Models
Fri, 27-Mar	Lecture 19 : Midterm Exam Review / Hidden Markov Models (Part I) [Slides] [Whiteboard] [Video] [Poll]	[Only pages 257 - 266] A Tutorial on Hidden Markov Models and Selected Applications in Speech Recognition. Rabiner (1989).	HW6 due Exam 2 practice problems out (Thu) HW5 Solution Session
Mon, 30-Mar	Lecture 20 : Hidden Markov Models (Part II) [Slides] [Whiteboard] [Video] [Poll]
Wed, 1-Apr	Lecture 21 : Bayesian Networks [Slides] [Whiteboard] [Video] [Poll]	Directed Graphical Models (Bayes nets). Kevin P. Murphy (2014). Machine Learning: A Probabilistic Perspective. Chapter 10.	HW6 Solution Session
Thu, 2-Apr	Midterm Exam 2 (6:00PM - 9:00PM) -- details will be announced on Piazza		HW7 out
Fri, 3-Apr	Recitation: HW7 [Video]
Reinforcement Learning
Mon, 6-Apr	Lecture 22 : Reinforcement Learning: Markov Decision Processes [Slides] [Whiteboard] [Video] [Poll]	Reinforcement Learning: A Survey. Kaelbling, et al (1996).
Wed, 8-Apr	Lecture 23 : Reinforcement Learning: Value/Policy Iteration [Slides] [Whiteboard] [Video] [Poll]
Fri, 10-Apr	Recitation: HW8 [Video]		HW7 due HW8 out
Mon, 13-Apr	Lecture 24 : Reinforcement Learning: Q-Learning [Slides] [Whiteboard] [Video] [Poll]
Wed, 15-Apr	Lecture 25 : Deep Reinforcement Learning / K-Means [Slides] [Whiteboard] [Video] [Poll]	[Optional] Playing Atari with Deep Reinforcement Learning. Mnih, et al (2013).	HW7 Solution Session
Fri, 17-Apr	(No recitation)
Learning Paradigms
Mon, 20-Apr	Lecture 26 : Dimensionality Reduction: PCA [Slides] [Whiteboard] [Video] [Poll]	A Tutorial on Principal Component Analysis. Jonathon Shlens (2014).
Wed, 22-Apr	Lecture 27 : SVMs / Kernel Methods [Slides] [Whiteboard] [Video] [Poll]	Kernel Methods. Hal Daumé III (2017). CIML, Chapter 11.	HW8 due HW9 out
Fri, 24-Apr	Recitation: HW9 [Video]
Mon, 27-Apr	Lecture 28 : Ensemble Methods / Recommender Systems [Slides] [Whiteboard] [Video] [Poll]	A Brief Introduction to Boosting. Robert E. Schapire (1999). Matrix Factorization Techniques for Recommender Systems. Koren, Bell, and Volinsky (2009).	HW8 Solution Session
Wed, 29-Apr	Lecture 29 : Final Exam Review [Slides] [Whiteboard] [Video] [Poll]	10601 Learning Objectives. Matt Gormley (2018).	HW9 due Exam 3 practice problems out (Thu)
Fri, 1-May	(No recitation)		HW9 Solution Session (Saturday, May 02)
Mon, 4-May	Final Exam (1:00PM - 4:00PM) -- details will be announced on Piazza

Introduction to Machine Learning

Important Notes

Lecture Videos

Lecture Polls

Tentative Schedule

Classification & Regression

Linear Models

Deep Learning

Learning Theory

Generative Models

Graphical Models

Reinforcement Learning

Learning Paradigms