Course Introduction

Catalog Description
An introduction to a range of adaptive computer algorithms that learn models from data. Explores the theoretical foundations of machine learning, including computational learning theory and PAC learnability. Examples of machine learning algorithms studied include: decision trees, artificial neural networks, Bayesian learners, evolutionary algorithms and ensemble techniques. Prerequisite: EECE 6820 Artificial Intelligence or equiv. Students should also have strong programming skills in Python, discrete mathematics, and calculus.

Instructor
Cristinel (Cris) Ababei
cristinel.ababei@marquette.edu
Phone: 414-288-5720
Office: Haggerty Hall, #220

Syllabus
For course goals and objectives, policies, and a tentative outline please see the syllabus on D2L.

Textbook
There is no single required textbook. However, there are several books (selected chapters) and research articles that will be used as reading materials. The books marked with * are particularly looked at in this course.

Books for gentler/shorter introductions to machine learning:
--[*B1-Mostafa] Yasser Abu-Mostafa, Learning From Data - A Short Course, 2012. (Free Slides, Videos only online).
--[B1-Alpaydin] Ethem Alpaydin, Introduction to Machine Learning, 3rd edition, 2014. (Free Slides only online).
--[B1-James-Hastie] Gareth James, Daniela Witten, Trevor Hastie, and Robert Tibshirani, An Introduction to Statistical Learning: with Applications in Python, 2023. (ISL, Free PDF online).
--[B1-Daume] Hal Daume III, A Course in Machine Learning, 2017. (Free PDF online).

More elaborated presentations or reference books:
--[*B2-Murphy] Kevin Murphy, Probabilistic Machine Learning: An Introduction, 2022. (Free PDF online).
--[B2-Mohri] Mehryar Mohri, Afshin Rostamizadeh, and Ameet Talwalkar, Foundations of Machine Learning, 2nd edition, 2018. (Free PDF online).
--[B2-Hastie] Trevor Hastie, The Elements of Statistical Learning, 2017. (ESL, Free PDF online).
--[B2-Efron-Hastie] Bradley Efron and Trevor Hastie, Computer Age Statistical Inference: Algorithms, Evidence and Data Science, 2016/2021. (CASI, Free PDF online).
--[B2-Bishop] Christopher M. Bishop, Pattern Recognition and Machine Learning, 2006. (Free PDF online).
--[B2-Mitchell] Tom Mitchell, Machine Learning, 1997. (Free PDF online).

Books with an emphasis on coding (mostly in Python) and applications:
--[*B3-Geron] Aurelien Geron, Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow, O'Reilly, 2022. (Code available at GitHub).
--[*B3-Raschka] Sebastian Raschka, Yuxi Liu, and Vahid Mirjalili, Learning with PyTorch and Scikit-Learn: Develop machine learning and deep learning models with Python, Packt Publishing, 2022. (Code available at GitHub).
--[B3-Muller] Andreas C. Muller and Sarah Guido, Introduction to Machine Learning with Python: A Guide for Data Scientists, O'Reilly, 2016. (Code available at GitHub).
--[B3-Grus] Joel Grus, Data Science from Scratch with Python, O'Reilly, 2019. (Code available at GitHub).

Lectures, Code, HW, Readings

Lecture	Topic	Assignment	Code+	Readings, Videos
1	Introduction --Slides1 --Notes1 --Notes: fitting, MLE/MAP, Ein(g), Eout(g)	Assignment 1	lec01_files.zip [B3-Geron] Linear Algebra [B3-Geron] Differential Calculus	Review of deep learning (PDF)
	Supervised learning: linear models
2	Linear regression Linear regression with basis functions --Slides2 part1 --Notes2 part1, Notes2 part2 Bias-variance trade-off Regularization; Ridge regression --Slides2 part2 --Notes2 part3, Notes2 part4	Assignment 2 Assignment 3	lec02_files.zip	Ch.3 Linear Regression (PDF) Paper review #1
3	Gradient descent --Slides3 --Notes3	Assignment 4	lec03_files.zip	Overview of GD (PDF) GD, Stochastic Optimization, Tales (PDF)
4	Logistic regression --Slides4 --Notes4	Assignment 5	lec04_files.zip	Paper review #2
	Supervised learning: non-linear models
5	Neural Networks MLP --Slides5 part1 --Notes5 part1 CNN --Slides5 part2 --Notes5 part2 LSTM --Slides5 part3	Assignment 6 Assignment 7 Assignment 8	lec05_files.zip	Ch.4 Neural Networks (PDF) ImageNet Classification with CNN (PDF)
6	Non-parametric methods; k Nearest Neighbors (kNN) Kernel methods; Bootstrap --Slides6	Assignment 9	lec06_files.zip	Ch.2 Kernel methods (PDF) SVM survey paper (PDF)
	Unsupervised learning
7	Principal component analysis (PCA) --Slides7	Assignment 10	lec07_files.zip	Ch.10 Dim reduction PCA (PDF) Paper review #3
8	K-means; Gaussian mixture models (GMMs) --Slides8	Assignment 11	lec08_files.zip	Ch.8 Clustering (PDF)
	Other/Advanced Topics
9	Combining Multiple Learners --Slides9	Assignment 12	lec09_files.zip	Ch.11 Ensemble methods (PDF) Ch.13 Ensemble methods (PDF)
10	Reinforcement Learning (RL) --Slides10	Assignment 13	lec10_files.zip	Paper review #4 RL - a brief intro RL - an overview Reinforcement Learning (Book, PDF)
11	Large Language Models (LLMs) --Slides11	Assignment 14	lec11_files.zip	Ch.8 Transformers (PDF) Original transformer (PDF) Transformer illustrated LLM Council
12	Graph Neural Networks (GNNs) --Slides12	Assignment 15	lec12_files.zip	Original graph convolutions (PDF)

Resources

Related resources and videos on ML:

One of the most fantastic online resources is Jason Brownlee's website with plenty of excellent tutorials.
--Jason Brownlee, Tutorials at machinelearningmastery.com.

Some remarkable videos, in no particular order.
--Yasser Abu-Mostafa, Caltech, Machine Learning Course - CS 156. 2012. Uses [B1-Mostafa].
--Andrew Ng, Stanford, CS229: Machine Learning. 2018. Suggests [B2-Bishop].
--Trevor Hastie, Stanford, Statistical Learning Course I ISLP Python. 2023. Uses [B1-James-Hastie].
--Jure Leskovec, Stanford, CS224W: Machine Learning with Graphs. 2021.
--Kilian Weinberger, Cornell, CS4780 Machine Learning for Decision Making. 2017. Uses [B2-Murphy], 2012 edition.
--Sergey Levine, Berkeley, CS 182 Deep Learning. 2021.
--Tom Mitchell, CMU, 10-601 Machine Learning. 2015. Uses [B2-Mitchell] and [B2-Bishop].

Refreshing your background:

Probability:
--Arian Maleki and Tom Do, Review of Probability Theory
--Roy D. Yates and David J. Goodman, Probability and Stochastic Processes: A Friendly Introduction for Electrical and Computer Engineers, 2005.
--Arian Maleki and Tom Do, Review of Probability Theory

Algebra, Matrix Analysis, Calculus:
--Pederson and Pederson, The Matrix Cookbook
--Zico Kolter and Chuong Do, Linear Algebra Review and Reference
--David Cherney, Tom Denton, Rohit Thomas and Andrew Waldron, Linear Algebra
--Marc Peter Deisenroth, A. Aldo Faisal, and Cheng Soon Ong, Mathematics for Machine Learning

Optimization:
--Moritz Diehl, Lecture Notes on Numerical Optimization (Preliminary Draft)
--Mykel J. Kochenderfer and Tim A. Wheeler, Algorithms for Optimization
--Sebastien Bubeck, Convex Optimization: Algorithms and Complexity
--Stephen Boyd and Lieven Vandenberghe, Convex Optimization

Python:
--Allen B. Downey, Think Python
--Interactive Python tutorial
--Google's Python Class