Sep 11

Lecture 1

Introduction and Basic Concepts. Linear Algebra and Multivariable Calculus review.

Reading:
Notes on Linear Algebra.
Lecture 1 Slides.

Before the Lecture:
Recommended: Review background materials on Linear Algebra and Multivariable Calculus.

During Lecture:
Synchronous: Overview of machine learning and the course.
Asynchronous: Review of linear algebra and multivariable calculus.

Sep 18

Lecture 2

Supervised Learning Setup. Linear Regression. Basic probability theory review.

Reading:
Notes on Basic Probability
Sections 1-3 of the notes on Supervised Learning Setup & Linear Regression.

Before the Lecture:
Recommended: Review background materials on Basic Probability.

During Lecture:
Synchronous: Supervised Learning Setup. Linear Regression.
Asynchronous: Basic probability theory review.

Sep 20

Assignment 1

Assignment 1 will be posted online.

Sep 25

Lecture 3

Weighted Least Squares. Logistic Regression. Newton's Method. Exponential Family. Generalized Linear Models. Python overview.

Reading:
Sections 4-9 of the notes on Regression.

Before the Lecture:
Recommended: Review background materials on Python.

During Lecture:
Synchronous: Weighted Least Squares. Logistic Regression. Newton's Method.
Asynchronous: Exponential Family. Generalized Linear Models. Python overview.

Oct 2

Project Proposal

Project proposal due at noon (i.e., 12 PM) eastern time.

Oct 2

Lecture 4

Evaluation Metrics. Gaussian Discriminant Analysis. Naive Bayes.

Reading:
Sections 1-2 of the notes on Generative Models.

Before the Lecture:
Recommended: Review class notes.

During Lecture:
Synchronous: Gaussian Discriminant Analysis. Naive Bayes.
Asynchronous: Evaluation Metrics.

Oct 9

Assignment 1

Assignment 1 due at noon (i.e., 12 PM) eastern time.

Oct 9

Lecture 5

Laplace Smoothing. Support Vector Machines.

Reading:
Sections 2 of the notes on Generative Models.
Sections 1-5, 7 of the notes on Kernels and SVM.

Before the Lecture:
Recommended: Review class notes.

During Lecture:
Synchronous: Laplace Smoothing. Support Vector Machines.
Asynchronous: Support Vector Machines.

Oct 18

Assignment 2

Assignment 2 will be posted online.

Oct 23

Lecture 6

Neural Networks, forward and backpropagation. Improving NNs.

Reading:
Notes on Deep Learning and Backpropagation.

Before the Lecture:
Recommended: Review class notes.

During Lecture:
Synchronous: Neural Networks, forward and backpropagation.
Asynchronous: Improving NNs.

Oct 30

Lecture 7

Deep learning, CNNs, RNNs, and beyond. Practical advice for your project.

Reading:
Lecture notes and slides will be posted after the lecture.

Before the Lecture:
Recommended: Have a very good sense of your progress in the project and challenges you are currently facing. You should be about halfway through your project.

During Lecture:
Synchronous: Practical advice for your project.
Asynchronous: Deep learning, CNNs, RNNs, and beyond.

Nov 6

Assignment 2

Assignment 2 due at noon (i.e., 12 PM) eastern time.

Nov 6

Lecture 8

Regularization. Feature/Model selection. K-Means. GMM.

Reading:
Notes on Regularization. Feature/Model selection.
Notes on k-means.
Notes on GMM.

Before the Lecture:
Recommended: Review class notes.

During Lecture:
Synchronous: K-Means. GMM.
Asynchronous: Regularization. Feature/Model selection.

Nov 8

Assignment 3

Assignment 3 will be posted online.

Nov 13

Lecture 9

Decision Trees. Boosting. Bagging. Principal and Independent Component Analysis.

Reading:
Notes on Principal Component Analysis.
Notes on Independent Component Analysis.

Before the Lecture:
Recommended: Review class notes.

During Lecture:
Synchronous: Principal and Independent Component Analysis.
Asynchronous: Decision Trees. Boosting. Bagging.

Nov 20

Lecture 10

Weak supervision. Critiques of Machine Learning.

Reading:
Notes on Weak Supervision.

Before the Lecture:
Recommended: Review class notes.

During Lecture:
Synchronous: Weak supervision.
Asynchronous: Critiques of Machine Learning.

Nov 27

Assignment 3

Assignment 3 due at noon (i.e., 12 PM) eastern time.

Nov 27

Lecture 11

Reinforcement learning. Value Iteration and Policy Iteration. Bias Variance trade-off.

Reading:
Notes on Reinforcement learning.
Notes on Bias Variance trade-off.

Before the Lecture:
Recommended: Review class notes.

During Lecture:
Synchronous: Reinforcement learning. Value Iteration and Policy Iteration.
Asynchronous: Bias Variance trade-off.

Dec 4

Lecture 12

Advanced topics. Guest Lectures. Course wrap up.

Reading:
Lecture notes and slides will be posted after the lecture.

During Lecture:
Synchronous: Guest lectures. Course wrap up.
Asynchronous: Advanced topics.

Dec 15

Final Project

Final Project due at noon (i.e., 12 PM) eastern time.