10-601 Spring 2018

Important Notes

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

Lecture Videos

Panopto folder: [Andrew ID Required] 10-601 A/C
Panopto folder: [Andrew ID Required] 10-601 B/D
The above folders contains all the lecture video recordings for the specified section. To access them, you will need to log in with your Andrew ID.
We have also included links to individual videos below -- however, we recommend checking the link above to find the latest videos.

Tentative Schedule

Date	Lecture	Readings	Announcements
Classification
Wed, 17-Jan	Lecture 1 : Course Overview [Slides] [Video A/C] [Video B/D]	Visual Information Theory. Christopher Olah (2015). blog.	HW1 out
Mon, 22-Jan	Lecture 2 : Decision Trees [Slides] [Video A/C] [Video B/D]	Decision Trees. Hal Daumé III (2017). CIML, Chapter 1. Limits of Learning. Hal Daumé III (2017). CIML, Chapter 2.
Wed, 24-Jan	Lecture 3 : k-Nearest Neighbors [Slides] [Video A/C] [Video B/D]	Geometry and Nearest Neighbors. Hal Daumé III (2017). CIML, Chapter 3.	HW2 out
Fri, 26-Jan	Recitation: HW2
Mon, 29-Jan	Lecture 4 : Model Selection [Slides] [Video A/C] [Video B/D]	10601 Notation Crib Sheet. Matt Gormley (2018).
Wed, 31-Jan	Lecture 5 : Perceptron [Slides] [Video A/C] [Video B/D]	The Perceptron. Hal Daumé III (2017). CIML, Chapter 4.
Fri, 2-Feb	Recitation: Math Background
Linear Models
Mon, 5-Feb	Lecture 6 : Linear Regression [Slides] [Video A/C] [Video B/D]	Linear Regression. Kevin P. Murphy (2014). Machine Learning: A Probabilistic Perspective. Chapter 7.1-7.3.	HW2 due
Wed, 7-Feb	Lecture 7 : Optimization for ML [Slides] [Video A/C] [Video B/D]	Optimization lecture notes from 10-600. Geoff Gordon (2016).	HW3 out
Fri, 9-Feb	Recitation: HW3
Mon, 12-Feb	Lecture 8 : Probabilistic Learning [Slides] [Video A/C] [Video B/D]	Estimating Probabilities: MLE and MAP. Tom Mitchell (2016, draft).
Wed, 14-Feb	Lecture 9 : Logistic Regression [Slides] [Video A/C] [Video B/D]	Logistic Regression. Kevin P. Murphy (2014). Machine Learning: A Probabilistic Perspective. Chapter 1.4.6, 8.1-8.3, 8.6.	HW3 due
Fri, 16-Feb	Recitation: HW4		HW4 out
Mon, 19-Feb	Lecture 10 : Regularization [Slides] [Video A/C] [Video B/D]	Regularization for Deep Learning. Ian Goodfellow, Yoshua Bengio, & Aaron Courville (2016). Deep Learning, Chapter 7.1 and 7.8.
Deep Learning
Wed, 21-Feb	Lecture 11 : Neural Networks [Slides] [Video A/C] [Video B/D]	Deep Feedforward Networks. Ian Goodfellow and Yoshua Bengio and Aaron Courville (2016). Deep Learning, Chapter 6.1-6.4.
Fri, 23-Feb	Lecture 12 : Backpropagation (Monday's lecture moved here) [Slides] [Video A/C] [Video B/D]	Deep Feedforward Networks. Ian Goodfellow, Yoshua Bengio, & Aaron Courville (2016). Deep Learning, Chapter 6.5.	HW4 due (Sun)
Mon, 26-Feb	Lecture 13 : Guest Lecture: Convolutional Neural Networks (CNNs), 12:00 - 12:50 PM only (see Piazza for details) [Slides] [Video B/D]	[Optional] Deep learning. Yann LeCun, Yoshua Bengio, & Geoffrey Hinton (2015). Nature.	HW5 out
Wed, 28-Feb	Lecture 14 : Backpropagation (cont.) [Slides] [Video A/C] [Video B/D]	Deep Feedforward Networks. Ian Goodfellow, Yoshua Bengio, & Aaron Courville (2016). Deep Learning, Chapter 6.5.
Fri, 2-Mar	Recitation: HW5
Learning Theory
Mon, 5-Mar	Lecture 15 : Learning Theory: PAC Learning [Slides] [Video A/C] [Video B/D]	Generalization Abilities: Sample Complexity Results.. Nina Balcan (2015). Lecture notes.
Wed, 7-Mar	Lecture 16 : Learning Theory: PAC Learning / Midterm Exam Review [Slides] [Video A/C] [Video B/D]	A Few Useful Things to Know about Machine Learning. Pedro Domingos (2012).
Fri, 9-Mar	Lecture 17 : Guest Lecture: Recurrent Neural Networks (RNNs), 12:00 - 12:50 PM only (see Piazza for details) [Slides] [Video B/D]		HW5 due (Fri)
Mon, 12-Mar	(No class: Midsemester break)
Wed, 14-Mar	(No class: Midsemester break)
Mon, 19-Mar	Lecture 18 : Learning Theory: Structured Risk Minimization [Slides] [Video A/C] [Video B/D]	Generalization Abilities: Sample Complexity Results.. Nina Balcan (2015). Lecture notes.
Generative Models
Wed, 21-Mar	Lecture 19 : Oracles, Sampling, Generative vs. Discriminative [Slides] [Video A/C] [Video B/D]
Thu, 22-Mar	Midterm Exam (Evening Exam) -- details will be announced on Piazza	10601 Learning Objectives. Matt Gormley (2018).
Fri, 23-Mar	(No recitation)
Mon, 26-Mar	Lecture 20 : MLE and MAP [Slides] [Video A/C] [Video B/D]	Estimating Probabilities: MLE and MAP. Tom Mitchell (2016, draft).
Wed, 28-Mar	Lecture 21 : Naive Bayes [Slides] [Video A/C] [Video B/D]	Generative and Discriminative Classifiers: Naive Bayes and Logistic Regression. Tom Mitchell (2016, draft).	HW6 out
Fri, 30-Mar	Recitation: HW6
Graphical Models
Mon, 2-Apr	Lecture 22 : Hidden Markov Models (Part I) [Slides] [Video A/C] [Video B/D]	[Only pages 257 - 266] A Tutorial on Hidden Markov Models and Selected Applications in Speech Recognition. Rabiner (1989).
Wed, 4-Apr	Lecture 23 : Hidden Markov Models (Part II) [Slides] [Video A/C] [Video B/D]		HW7 out HW6 due
Fri, 6-Apr	Recitation: HW7
Mon, 9-Apr	Lecture 24 : Bayesian Networks [Slides] [Video A/C] [Video B/D]	Directed Graphical Models (Bayes nets). Kevin P. Murphy (2014). Machine Learning: A Probabilistic Perspective. Chapter 10.
Learning Paradigms
Wed, 11-Apr	Lecture 25 : Reinforcement Learning (Part I) [Slides] [Video A/C] [Video B/D]	Reinforcement Learning: A Survey. Kaelbling, et al (1996).
Fri, 13-Apr	Lecture 26 : Reinforcement Learning (Part II) [Slides] [Video A/C] [Video B/D]
Mon, 16-Apr	Lecture 27 : Deep Reinforcement Learning [Slides] [Video A/C] [Video B/D]	[Optional] Playing Atari with Deep Reinforcement Learning. Mnih, et al (2013).	HW8 out HW7 due
Wed, 18-Apr	Lecture 28 : SVMs [Slides] [Video A/C] [Video B/D]	Kernel Methods. Hal Daumé III (2017). CIML, Chapter 11.
Fri, 20-Apr	(No Recitation: Spring Carnival)
Mon, 23-Apr	Recitation: HW8
Wed, 25-Apr	Lecture 29 : Kernels / K-Means [Slides] [Video A/C] [Video B/D]
Fri, 27-Apr	Lecture 30 : PCA / Boosting [Slides] [Video A/C] [Video B/D]	A Tutorial on Principal Component Analysis. Jonathon Shlens (2014). A Brief Introduction to Boosting. Robert E. Schapire (1999).	HW9 out HW8 due
Mon, 30-Apr	Recitation: HW9

Wed, 2-May	Lecture 31 : Final Exam Review [Slides] [Video A/C] [Video B/D]	10601 Learning Objectives. Matt Gormley (2018).
Fri, 4-May	Recitation: Final Exam Review		HW9 due
14-May	Final Exam 1:00 PM - 4:00 PM

Introduction to Machine Learning

Important Notes

Lecture Videos

Tentative Schedule

Classification

Linear Models

Deep Learning

Learning Theory

Generative Models

Graphical Models

Learning Paradigms