Machine Learning (ICS 435/635) is a thorough and rigorous introduction to Machine Learning. After completing this course, you will understand the fundamentals of Machine Learning theory and implementation in Python. A side goal of this class is to make math (Linear Algebra, Calculus, Probability and Statistics) fun! You are not required to take those math courses prior to this class - we will cover the required math on an as-needed basis.
This course provides an introduction to key theoretical and practical concepts of machine learning. While we will cover material starting from the beginning, we will move quickly in order to provide a full overview of machine learning. It is therefore highly recommended to have prior exposure at the level of ICS 235: Machine Learning Fundamentals or the equivalent. The homework assignments involve a good amount of Python coding, so it is required to already be familiar with programming in general and have the will and ability to quickly learn Python if you do not know Python already.
| Date | Topic | Assignment Due (midnight before class) |
|---|---|---|
| Tues Jan 10 | Overview of Machine Learning (ML) (Notes) | |
| Thur Jan 12 | Linear Regression and Intro to Loss Functions (Notes) | |
| Tues Jan 17 | Logistic Regression and ML Evaluation Part 1 (Notes) | |
| Thur Jan 19 | ML Evaluation Part 2 and Calculus Review (Notes) | |
| Tues Jan 24 | Real-World Coding: Python Coding and Libraries (Video + Code on Laulima) | |
| Thur Jan 26 | Real-World Coding: Car Price Prediction (Video + Code on Laulima) | |
| Tues Jan 31 | Real-World Coding: Breast Cancer and Sentiment Prediction (Video + Code on Laulima) | |
| Thur Feb 02 | Gradient Descent (Notes) | Homework 1 due |
| Tues Feb 07 | Regularization and Probability Review (Notes) | |
| Thur Feb 09 | Maximum Likelihood, KNN, and Naive Bayes Intro (Notes) | |
| Tues Feb 14 | Naive Bayes and Decision Trees (Notes) | Homework 2 due |
| Thur Feb 16 | Ensemble Learning (Notes) | |
| Tues Feb 21 | Linear Algebra Review and SVMs (Notes) | |
| Thur Feb 23 | Kernels and Clustering (Notes) | |
| Tues Feb 28 | Midterm Review (Notes) | |
| Thur Mar 02 | Feature Selection and Engineering (Notes) | |
| Tues Mar 07 | Final project overview for ICS/DATA 435 (Notes) | Midterm Exam due (on Laulima) |
| Thur Mar 09 | Final project overview for ICS 635 (Notes) | |
| Spring Break | ||
| Tues Mar 21 | Recommender Systems and PCA (Notes) | Homework 3 due |
| Thur Mar 23 | Intro to Neural Networks / Deep Learning (Notes) | |
| Tues Mar 28 | CNNs, Transfer Learning, and Autoencoders (Notes) | |
| Thur Mar 30 | Real-World Coding: Dog vs Road Classification (Video + Code on Laulima) | |
| Tues Apr 04 | Real-World Coding: TensorFlow and Healthcare (Video + Code on Laulima) | |
| Thur Apr 06 | Segmentation, Detection, Generation (Notes) | |
| Tues Apr 11 | GANs, RNNs, Attention (Notes) | Homework 4 due |
| Thur Apr 13 | Real-World Coding: GANs, RNNs (Video + Code on Laulima) | |
| Tues Apr 18 | Transformers, Self-Supervised Learning (Notes from last time) | |
| Thur Apr 20 | Reinforcement Learning (Notes) | |
| Tues Apr 25 | Project Videos Part 1 | Final Project Presentation Video due |
| Thur Apr 27 | Project Videos Part 2 | |
| Tues May 02 | Course/Final Exam Review (and Putting It All Together: How ChatGPT Works) (Notes) | Homework 5 due |
| Finals Period | ||
| Tues May 09 | Final Project Report due | |
| Mon May 15 | Final Exam due at 5pm (on Laulima) |
Peter Washington is an Assistant Professor of Information and Computer Sciences at the University of Hawaii at Manoa. His research interests include developing data science methods to support machine learning for health and wellbeing, crowdsourcing for precision health, and digital interventions.