Lecture 1 (Tue 2/7): Introduction
Lecture 2 (Thu 2/9): Linear classifiers, separability, perceptron algorithm
HW 0 Due (Fri 2/10)
Lecture 3 (Tue 2/14): Maximum margin hyperplane, loss, regularization
Lecture 4 (Thu 2/16): Stochastic gradient descent, over-fitting, generalization
HW 1 Due (Fri 2/17)
Monday schedule of classes (Tue 2/21)
Lecture 5 (Thu 2/23): Linear regression
Combined HW 1,2 Due (Fri 2/24)
Lecture 6 (Tue 2/28): Recommender problems, collaborative filtering
Lecture 7 (Thu 3/2): Non-linear classification, kernels
Project 1 Due (Fri 3/3)
Lecture 8 (Tue 3/7): Learning features, Neural networks
Lecture 9 (Thu 3/9): Deep learning, backpropagation
HW 3 Due (Fri 3/10)
Lecture 10 (Tue 3/14): Recurrent neural networks
Lecture 11 (Thu 3/16): Recurrent neural networks
HW 4 Due (Fri 3/17)
Lecture 12 (Tue 3/21): Demo day; hands-on deep learning
MIDTERM EXAM (Thu 3/23): in class, 26-100
Spring break (Tue 3/28)
Spring break (Thu 3/30)
Lecture 13 (Tue 4/4): Generalization, complexity, VC-dimension
Lecture 14 (Thu 4/6): Unsupervised learning: clustering
Project 2 Due (Fri 4/7)
Lecture 15 (Tue 4/11): Generative models, mixtures
Lecture 16 (Thu 4/13): Mixtures and the EM algorithm
Patriot's day vacation (Tue 4/18)
Lecture 17 (Thu 4/20): Probability models: Hidden Markov Models
HW 5 Due (Fri 4/21)
Lecture 18 (Tue 4/25): Probability models: Bayesian networks
Lecture 19 (Thu 4/27): Probabilistic modeling, inference
Lecture 20 (Tue 5/2): Learning to control: Reinforcement learning
Lecture 21 (Thu 5/4): Reinforcement learning cont'd
Project 3 Due (Fri 5/5)
Lecture 22 (Tue 5/9): Applications: tbd
Lecture 23 (Thu 5/11): Applications: tbd
Lecture 24 (Tue 5/16): Applications: tbd
Lecture 25 (Thu 5/18): Exam review, wrap-up