10-601BD Fall 2018

Important Notes

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

Lecture Videos

Panopto folder: [Andrew ID Required] 10-601 B/D
The above folders contains all the lecture video recordings for the specified section(s). To access them, please select Sign in using "Canvas".
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
Mon, 27-Aug	Lecture 1 : Course Overview [Slides] [Video]	Visual Information Theory. Christopher Olah (2015). blog.
Wed, 29-Aug	Lecture 2 : Decision Trees [Slides] [Video]	Decision Trees. Hal Daumé III (2017). CIML, Chapter 1.	HW1 out
Fri, 31-Aug	Recitation: HW1 [Video]
Mon, 3-Sep	No Class: Labor Day
Wed, 5-Sep	Lecture 3 : Decision Trees [Slides] [Video]	Limits of Learning. Hal Daumé III (2017). CIML, Chapter 2.	HW2 out HW1 due
Fri, 7-Sep	Recitation: HW2 [Video]
Mon, 10-Sep	Lecture 4 : k-Nearest Neighbors [Slides] [Video]	Geometry and Nearest Neighbors. Hal Daumé III (2017). CIML, Chapter 3.
Wed, 12-Sep	Lecture 5 : Model Selection [Slides] [Video]	10601 Notation Crib Sheet. Matt Gormley (2018).
Fri, 14-Sep	(No Recitation)
Linear Models
Mon, 17-Sep	Lecture 6 : Perceptron [Slides] [Video]	The Perceptron. Hal Daumé III (2017). CIML, Chapter 4.
Wed, 19-Sep	Lecture 7 : Linear Regression / Optimization for ML [Slides] [Video]	Optimization lecture notes from 10-600. Geoff Gordon (2016). Linear Regression. Kevin P. Murphy (2014). Machine Learning: A Probabilistic Perspective. Chapter 7.1-7.3.	HW3 out HW2 due
Fri, 21-Sep	Recitation: HW3 [Video]
Mon, 24-Sep	Lecture 8 : Probabilistic Learning [Slides] [Video]	Estimating Probabilities: MLE and MAP. Tom Mitchell (2016, draft).
Wed, 26-Sep	Lecture 9 : Logistic Regression [Slides] [Video]	Logistic Regression. Kevin P. Murphy (2014). Machine Learning: A Probabilistic Perspective. Chapter 1.4.6, 8.1-8.3, 8.6.
Fri, 28-Sep	Recitation: HW4 [Video]		HW4 out (Sun) HW3 due
Mon, 1-Oct	Lecture 10 : Regularization [Slides] [Video]	Regularization for Deep Learning. Ian Goodfellow, Yoshua Bengio, & Aaron Courville (2016). Deep Learning, Chapter 7.1 and 7.8.
Deep Learning
Wed, 3-Oct	(Lecture cancelled. Watch the short video excerpt from my Spring 2018 lecture linked below instead.) [Video]
Fri, 5-Oct	(No recitation)
Mon, 8-Oct	Lecture 11 : Neural Networks (video only, see Piazza for details) [Slides] [Video]	Deep Feedforward Networks. Ian Goodfellow and Yoshua Bengio and Aaron Courville (2016). Deep Learning, Chapter 6.1-6.4.	HW5 out (Tue) HW4 due (Tue)
Wed, 10-Oct	Lecture 12 : Backpropagation (video only, see Piazza for details) [Slides] [Video]	Deep Feedforward Networks. Ian Goodfellow, Yoshua Bengio, & Aaron Courville (2016). Deep Learning, Chapter 6.5.
Fri, 12-Oct	Recitation: HW5 [Video]
Mon, 15-Oct	Lecture 13 : Understanding Linear and Nonlinear Decision Boundaries [Slides] [Video]	[Optional] Deep learning. Yann LeCun, Yoshua Bengio, & Geoffrey Hinton (2015). Nature.
Learning Theory
Wed, 17-Oct	Lecture 14 : Learning Theory: PAC Learning [Slides] [Video]	Generalization Abilities: Sample Complexity Results.. Nina Balcan (2015). Lecture notes.
Fri, 19-Oct	(No Recitation)		HW5 due (Sat)
Mon, 22-Oct	Lecture 15 : Midterm Exam Review / Learning Theory: PAC Learning [Slides] [Video]	10601 Learning Objectives. Matt Gormley (2018). A Few Useful Things to Know about Machine Learning. Pedro Domingos (2012).
Generative Models
Wed, 24-Oct	Lecture 16 : Learning Theory: Structured Risk Minimization [Slides] [Video]
Thu, 25-Oct	Midterm Exam (Evening Exam, 6:30 PM - 9:30 PM) -- details will be announced on Piazza
Fri, 26-Oct	(No Class: CMU Presidential Inauguration)
Mon, 29-Oct	Lecture 17 : MLE and MAP [Slides] [Video]	Estimating Probabilities: MLE and MAP. Tom Mitchell (2016, draft).
Wed, 31-Oct	Lecture 18 : Naive Bayes [Slides] [Video]	Generative and Discriminative Classifiers: Naive Bayes and Logistic Regression. Tom Mitchell (2016, draft).	HW6 out
Fri, 2-Nov	Recitation: HW6 [Video]
Graphical Models
Mon, 5-Nov	Lecture 19 : Hidden Markov Models (Part I) [Slides] [Video]	[Only pages 257 - 266] A Tutorial on Hidden Markov Models and Selected Applications in Speech Recognition. Rabiner (1989).
Wed, 7-Nov	Lecture 20 : Hidden Markov Models (Part II) [Slides] [Video]		HW7 out HW6 due
Fri, 9-Nov	Recitation: HW7 [Video]
Mon, 12-Nov	Lecture 21 : Bayesian Networks [Slides] [Video]	Directed Graphical Models (Bayes nets). Kevin P. Murphy (2014). Machine Learning: A Probabilistic Perspective. Chapter 10.
Learning Paradigms
Wed, 14-Nov	Lecture 22 : Reinforcement Learning: Value/Policy Iteration [Slides] [Video]	Reinforcement Learning: A Survey. Kaelbling, et al (1996).
Fri, 16-Nov	Lecture 23 : Reinforcement Learning: Q-Learning [Slides] [Video]	[Optional] Playing Atari with Deep Reinforcement Learning. Mnih, et al (2013).
Mon, 19-Nov	Lecture 24 : Deep Reinforcement Learning [Slides] [Video]		HW8 out HW7 due
Wed, 21-Nov	(No Class: Thanksgiving Break)
Fri, 23-Nov	(No Class: Thanksgiving Break)
Mon, 26-Nov	Recitation: HW8 [Video]
Wed, 28-Nov	Lecture 25 : SVMs [Slides] [Video]	Kernel Methods. Hal Daumé III (2017). CIML, Chapter 11.
Fri, 30-Nov	Lecture 26 : Kernels / K-Means [Slides] [Video]		HW9 out HW8 due
Mon, 3-Dec	Lecture 27 : PCA / Boosting [Slides] [Video]	A Tutorial on Principal Component Analysis. Jonathon Shlens (2014). A Brief Introduction to Boosting. Robert E. Schapire (1999).
Wed, 5-Dec	Recitation: HW9 [Video]
Fri, 7-Dec	Recitation: Final Exam Review [Slides] [Video]	10601 Learning Objectives. Matt Gormley (2018).	HW9 due
Thu, 13-Dec	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