**EECS 498: Principles of Machine Learning, Fall 202**2

**Course** **Instructor:** Prof. Laura Balzano, Prof. Qing Qu, Prof. Lei Ying

(listed in alpha beta order, please contact Prof. Qing Qu for more details)

**Teaching Assistant:** Alexander Ritchie

**Title: **Principles of Machine Learning

**Course Time:** Mon/Wed 1:30 PM – 3:00 PM, 3 credit hour

**Office Hour**: Wed 3:30 PM – 5:00 PM

**Prerequisite:** EECS 351, or EECS 301, or any linear algebra courses

**Notice:** This is an entry-level machine learning course targeted for senior undergraduate and junior master students. **This course is a little bit more emphasis on mathematical principles in comparison to EECS 445.** Students outside the ECE program interested in machine learning are welcome as well!

**Overview**: The class will cover basic principles in machine learning, such as unsupervised learning (e.g., clustering, mixture models, dimension reduction), supervised learning (e.g., regression, classification, neural networks & deep learning), and reinforcement learning. For each topic, key algorithmic ideas/intuitions and basic theoretical insights will be highlighted.

**Course Materials:** slides and videos will be accessed via Canvas (TBA). Tentative topics that will be covered in this course are **supervised learning, unsupervised learning, and reinforcement learning**:

- Basics of probability, linear algebra, and optimization
- Regression and linear prediction
- Support vector machines and kernel methods
- Deep neural networks
- Dimension reduction: PCA, autoencoder
- Clustering (Kmeans, Mixture of Gaussians, EM)
- Representation learning: nonnegative matrix factorization, dictionary learning
- Basics of Online/reinforcement learning

**Assessment**: (i) homework assignment (5 in total, 40%), (ii) mid-term exam (30%), (iii) Final project (30%)

**Textbook:** We recommend the following books and articles, although we will not follow them closely.

- Foundations of Machine Learning, by Mehryar Mohri, Afshin Rostamizadeh, and Ameet Talwalkar.
- The Elements of Statistical Learning: Data Mining, Inference, and Prediction, by Trevor Hastie, Robert Tibshirani, and Jerome Friedman.
- Deep Learning, by Ian Goodfellow, Yoshua Bengio, and Aaron Courville.
- Mathematics for Machine Learning, by Marc Peter Deisenroth, A. Aldo Faisal, and Cheng Soon Ong.
- Linear Algebra and Optimization for Machine Learning, by Charu C. Aggarwal.

**Related courses**:

- EECS 445. Introduction to Machine Learning
- EECS 453. Applied Matrix Algorithms for Signal Processing, Data Analysis, and Machine Learning
- EECS 505. Computational Data Science and Machine Learning
- EECS 545. Machine Learning

**Syllabus:** (tentative)

Week | Date | Topic | Contents | Instructor | Homework, Review |

Week-1-1 | 08/30 | Introduction | Course overview | Qing Qu | |

Week-1-2 | 09/01 | Supervised Learning | Introduction to supervised learning, linear models, regularization | Qing Qu | Linear Algebra Review |

Week-2-1 | 09/06 | Labor Day | No class | | |

Week-2-2 | 09/08 | Supervised Learning | Logistic Regression | Qing Qu | Probability Review, HW1 Release |

Week-3-1 | 09/13 | Supervised Learning | Logistic Regression continued, optimization methods | Qing Qu | |

Week-3-2 | 09/15 | Supervised Learning | Optimization methods | Qing Qu | Python Review |

Week-4-1 | 09/20 | Supervised Learning | Linear classification, support vector machine (SVM) I | Qing Qu | |

Week-4-2 | 09/22 | Supervised Learning | Linear classification, support vector machine (SVM) II | Qing Qu | HW1 Due, HW2 Release |

Week-5-1 | 09/27 | Supervised Learning | Dual SVM | Qing Qu | |

Week-5-2 | 09/29 | Supervised Learning | Nonlinear models, kernel methods | Qing Qu | |

Week-6-1 | 10/04 | Supervised Learning | Introduction to deep neural networks I | Qing Qu | |

Week-6-2 | 10/06 | Supervised Learning | Introduction to deep neural networks II | Qing Qu | HW2 Due, HW3 Release |

Week-7-1 | 10/11 | Supervised Learning | Introduction to deep neural networks III | Qing Qu | |

Week-7-2 | 10/13 | Unsupervised Learning | Introduction to unsupervised learning, clustering problem, K-means | Qing Qu | |

Week-8-1 | 10/18 | Fall Study Day | No class | | |

Week-8-2 | 10/20 | Unsupervised Learning | K-means, mixtures of Gaussian, expectation maximization | Qing Qu | HW3 Due |

Week-9-1 | 10/25 | Midterm Review | Midterm Review | Qing Qu | |

Week-9-2 | 10/27 | Midterm | Midterm | Qing Qu | |

Week-10-1 | 11/01 | Unsupervised Learning | Dimension reduction, PCA | Qing Qu | |

Week-10-2 | 11/03 | Unsupervised Learning | Dimension reduction II | Qing Qu | HW4 Release, Project Proposal Due |

Week-11-1 | 11/08 | Unsupervised Learning | Representation learning, matrix factorization | Qing Qu | |

Week-11-2 | 11/10 | Unsupervised Learning | Representation learning, matrix factorization | Qing Qu | |

Week-12-1 | 11/15 | Unsupervised Learning | Autoencoder, self-supervised learning, GAN | Qing Qu | |

Week-12-2 | 11/17 | Unsupervised Learning | Autoencoder, self-supervised learning, GAN | Qing Qu | HW4 Due, HW5 Release |

Week-13-1 | 11/22 | Reinforcement Learning | TBD | Lei Ying | |

Week-13-2 | 11/24 | Thanksgiving | no class | | |

Week-14-1 | 12/01 | Reinforcement Learning | TBD | Lei Ying | |

Week-14-2 | 12/03 | Reinforcement Learning | TBD | Lei Ying | HW5 Due |

Week-15-1 | 12/06 | Final | Final project preparation | Qing Qu | |

Week-15-2 | 12/08 | Final | Final project presentation | Qing Qu |