## About CSC411/2515

This course serves as a broad introduction to machine learning and data mining. We will cover the fundamentals of supervised and unsupervised learning. We will focus on neural networks, policy gradient methods in reinforcement learning. We will use the Python NumPy/SciPy stack. Students should be comfortable with calculus, probability, and linear algebra.

## Teaching Team

Instructor | Section | Office Hour | ||
---|---|---|---|---|

Michael Guerzhoy | Th6-9 (SF1101) | M6-7, W6-7 (BA3219) | guerzhoy [at] cs.toronto.edu | |

Lisa Zhang | T1-3, Th2-3 (RW117) | Th11-12, 3:30-4:30 (BA3219) | lczhang [at] cs.toronto.edu |

When emailing instructors, please include "CSC411" in the subject.

Please ask questions on Piazza if they are relevant to everyone.

TA office hours are listed here.

## Study Guide

## Tentative Schedule

Day | Night | Content | Notes/Reading | Deadlines | |
---|---|---|---|---|---|

Review of Probability | Deep Learning 3.1-3.9.3 | Math Background Problem Set
Complete ASAP | |||

Review of Linear Algebra | Deep Learning 2.1-2.6 | ||||

Week 1 | Jan 4 | Jan 4 | Welcome; K-Nearest Neighbours |
| |

Jan 9 | Jan 4 | Linear Regression |
| ||

Jan 9 | Jan 4 | ||||

Week 2 | Jan 11 | Jan 11 | Numpy Demo:
html
ipynb
Numpy Images: html ipynb 3D Plots (contour plots, etc): html ipynb Gradient Descent (1D): html ipynb Gradient Descent (2D): html ipynb Linear Regression: html ipynb |
| |

Jan 16 | Jan 11 | Multiple Linear Regression Linear Classification (Logistic Regression) Maximum Likelihood Bayesian Inference |
| ||

Jan 16 | Jan 11 | ||||

Week 3 | Jan 18 | Jan 18 | Bayesian inference and regularization (updated) Unicorns Bayesian inference: html ipynb Overfitting in linear regression: html ipynb |
| |

Jan 22 | Jan 18 | Neural Networks |
| ||

Jan 22 | Jan 18 | ||||

Week 4 | Jan 25 | Jan 25 | PyTorch Basics ipynb, html; Maximum Likelihood with PyTorch (ipynb, html) ; Neural Networks in PyTorch, low-level programming (ipynb, html) and high-level programming (ipynb, html); If there is time, Justin Johnson's Dynamic Net (ipynb, html) |
| Project #1 due Jan 29th |

Jan 30 | Jan 25 | Neural Networks, continued. Neural Networks Optimization, Activation functions, multiclass classification with maximum likelihood |
| ||

Jan. 30 | Jan. 25 | ||||

Week 5 | Feb 1 | Feb 1 |
| Project #1 bonus due Feb 5th | |

Feb 6 | Feb 1 | ||||

Feb 6 | Feb 1 | Reading: CIML Ch. 8, Bishop 4.2.1-4.2.3, Andrew Ng, Generative Learning Algorithms | |||

Week 6 | Feb 8 | Feb 8 | Gaussian classifiers, Multivariate Gaussains (ipynb), Mixtures of Gaussians and k-Means |
| |

Feb 13 | Feb 8 | ||||

Feb 13 | Feb 8 | ||||

Week 7 | Feb 15 | Feb 15 | EM Tutorial: Gaussians, Binomial. | | Project #2 due Feb 23rd Grad Project Proposal due Feb 28th |

Reading Week | Feb 27 | Feb 15 | |||

Feb 27 | Feb 15 | ||||

Week 8 | Mar 1 | Mar 1 | Review Tutorial (8pm-9pm for evening section) |
| Midterm Mar 2nd 6pm-8pm EX320:A-Lin EX300:Liu-Z Midterm| Solution |

Mar 6 | Mar 1 | ||||

Mar 6 | Mar 1 | ||||

Week 9 | Mar 8 | Mar 8 | Neural Style Transfer, Deep Dream (evening section only) Evolution Strategies for RL (evening section only) |
| |

Mar 13 | Mar 8 | ||||

Mar 13 | Mar 8 | ||||

Week 10 | Mar 15 | Mar 15 | Reinforcement Learning tutorial |
| Project #3 due Mar 19th |

Mar 20 | Mar 15 | SVMs and Kernels | |||

Mar 20 | Mar 15 | ||||

Week 11 | Mar 22 | Mar 22 | SVMs and Kernels (Cont'd) |
| |

Mar 27 | Mar 22 | Ensembles | |||

Mar 27 | Mar 22 | ||||

Week 12 | Mar 29 | Mar 29 | Review Tutorial | Project #4 due Apr 2 | |

Apr 3 | Mar 29 | Overview: supervised learning; Overview: unsupervised learning GANs | Suggested reading: Ian Goodfellow, Generative Adversarial Networks tutorial at NIPS 2016 (skim for applications and the description of GANs). | ||

Apr 3 | Mar 29 | ||||

Final Examination (CSC411) | April 2018 exam timetable | ||||

CSC2515 Project | due Apr. 26 |