Introduction to Machine Learning

New York University - Fall 2018

Class is held in 60FA 110, Tue 6:45-8:25pm

Office hours

Tuesday 4-6pm, CDS 618: Lecturer, Iddo Drori

Friday 3-5pm, CDS 606: Section Leader, Ameya Shanbhag

Monday 6-8pm, CDS 606: Grader, Sanyam Kapoor

Thursday 3:30-5:30pm, CDS 606: Grader, Vikram Sunil Bajaj

Lectures

Lecture 1 (Tuesday, September 4): Introduction
Examples of supervised, unsupervised, and reinforcement learning
Review of probability, decision theory, information theory
Frequentist vs. Bayesian inference
Reading: CB Ch. 1, CASI Ch. 1-3
Optional: KM Ch. 1-2
Lab 1: Python, Numpy, Scipy, probability distributions, Colaboratory, Kaggle, Google dataset search.

Lecture 2 (Tuesday, September 11): Evaluating performance, optimization
Lab 2: Sklearn, ROC curve, AUC, F1 score, SGD.

Yom Kippur, no class (Tuesday, Septemebr 18)

Lecture 3 (Friday, September 21): Supervised Learning
Reading: CASI Ch. 8
Optional: KM Ch. 7-8, CB Ch. 3-4
Lab 3: Sklearn, linear regression, logistic regression.
Homework 1 out

Lecture 4 (Tuesday, September 25): Kernel Methods
Reading: CASI Ch. 19
Optional: CB Ch. 6-7
Lab 4: Sklearn, support vector machines.

Lecture 5 (Tuesday, October 2): Unsupervised Learning
Reading: KM Ch. 25
Optional: CB Ch. 9
Lab5 (Tuesday, October 9): Sklearm, principle component analysis. Homework 1 due, Homework 2 out

Fall Recess, no classes scheduled (Monday, October 8)

Legislative Day, no classes scheduled (Tuesday, October 9)

Lecture 6 (Tuesday, October 16): Random Forests and Gradient Boosting
Reading: CASI Ch. 17
Lab 6: XGBoost.
Homework 2 due, Term project selection

Lecture 7 (Tuesday, October 23): Neural Networks
Reading: CASI Ch. 18
Optional: KM Ch. 28, CB Ch. 5 Lab 7: TensorFlow.

Lecture 8 (Tuesday, October 30): Neural Networks, Reinforcement Learning
Lab 8: PyTorch.

Lecture 9 (Tuesday, November 6): Reinforcement Learning
Lab 9: Software libraries

Lecture 10 (Tuesday, November 13): Meta Learning, AutoML
Lab 10: Auto-sklearn, TPOT.

Lecture 11 (Tuesday, November 20): Bayesian Inference
Lab 11: Expectation maximization

Thanksgiving Recess (Wednesday, November 21 - Friday, November 23)

Lecture 12 (Tuesday, November 27): Sampling
Lab 12: Probabilistic programming and learning

Lecture 13 (Tuesday, December 4): Sparse Modeling
Reading: CASI Ch. 16
Lab 13: Sklearn l1, lasso

Lecture 14 (Tuesday, December 11): Review

Last day of Fall 2018 classes (Friday, December 14)

Final Exam in class (Tuesday, December 18) 8pm-9:50pm.

Textbooks

CASI Computer Age Statistical Inference: Algorithms, Evidence and Data Science, Bradley Efron and Trevor Hastie, Cambridge University Press, 2016 (available online @ stanford.edu)
KM Machine Learning: A probabilistic perspective, Kevin Murphy, MIT Press, 2012 (available online @ library.nyu.edu)
CB Pattern Recognition and Machine Learning, Christopher M. Bishop, Springer, 2011 (available online @ library.nyu.edu)