6.036 Introduction to Machine Learning (Spring 2016)


DRAFT schedule of lectures / assignments:

Lecture 1 (Tue 2/2): Introduction

Lecture 2 (Thu 2/4): Linear classifiers, separability, perceptron algorithm

Lecture 3 (Tue 2/9): On-line classifiers, passive-agressive

Lecture 4 (Thu 2/11): Maximum margin hyperplane, over-fitting, regularization

HW 1 Due (Fri 2/12)

Monday schedule of classes (Tue 2/16)

Lecture 5 (Thu 2/18): Linear regression

HW 2 Due (Fri 2/19)

Lecture 6 (Tue 2/23): Recommender problems, collaborative filtering

Lecture 7 (Thu 2/25): Non-linear classification, kernels

Project 1 Due (Fri 2/26)

Lecture 8 (Tue 3/1): Learning features, Neural networks

Lecture 9 (Thu 3/3): Deep learning, backpropagation

HW 3 Due (Fri 3/4)

Lecture 10 (Tue 3/8): Recurrent neural networks

Lecture 11 (Thu 3/10): Recurrent neural networks

HW 4 Due (Fri 3/11)

Lecture 12 (Tue 3/15): Deep learning architectures

MIDTERM EXAM (Thu 3/17): in class, 26-100

Spring break (Tue 3/22)

Spring break (Thu 3/24)

Lecture 13 (Tue 3/29): Generalization, complexity, VC-dimension

Lecture 14 (Thu 3/31): Clustering, criteria, k-means

Project 2 Due (Fri 4/1)

Lecture 15 (Tue 4/5): Generative models, mixtures

Lecture 16 (Thu 4/7): Mixtures and the EM algorithm

Lecture 17 (Tue 4/12): Representation of probability models: Bayesian networks

Lecture 18 (Thu 4/14): Hidden Markov Models: modeling

HW 5 Due (Fri 4/15)

Patriot's day vacation (Tue 4/19)

Lecture 19 (Thu 4/21): Hidden Markov Models: algorithms

Lecture 20 (Tue 4/26): Learning to control: Reinforcement learning

Lecture 21 (Thu 4/28): Reinforcement learning cont'd

Project 3 Due (Fri 4/29)

Lecture 22 (Tue 5/3): Applications: tbd

Lecture 23 (Thu 5/5): Applications: tbd

Lecture 24 (Tue 5/10): Applications: tbd

Lecture 25 (Thu 5/12): Exam review, wrap-up