AIN 311 - Foundations of Machine Learning Fall 2025 Instructor: Ahmet Burak Can Class Time: Monday, 12:40-15:30 Room: Computer Engineering Building, D10 Teaching Assistans: Sibel Kapan, Orhan Demirci, Emirhan Selim Textbooks A Course in Machine Learning (CIML), Hal Daumé III, 2017 (available online) Bayesian Reasoning and Machine Learning, David Barber, Cambridge University Press, 2012 (available online) Pattern Recognition and Machine Learning, Bishop, Springer, 2006 (available online) Machine Learning: A Probabilistic Perspective, Murphy, MIT Press, 2012 Probabilistic Machine Learning:An Introduction , Murphy, MIT Press, 2022 Machine Learning, Tom Mitchell, McGraw Hill, 1997 Artificial Intelligence, A Modern Approach, Third Edition, Stuart J. Russell and Peter Norvig, 2010 Grading: AIN 311 - Foundations of Machine Learning Pop Quizzes - 15% Midterm exam - 35%     (17/11/2025) Final exam - 50% Grading: AIN313 - Machine Learning Laboratory 4 Programming Assignments 5%-20%-20%-20% Programming Project (done in pairs) - 35% Communication All class communication will be done via Piazza AIN311 communication group. Please register to this group on Piazza.com For the laboratory class of this course, please also register to Piazza AIN313 communication group Syllabus Resources Introduction     Machine Learning Methodology     KNN algorithm     Reading: CIML, Chapter 3.1-3.3 Decision Trees     Reading: Mitchell, Chapter 3 CIML, Chapter 1 Bayesian Learning     Reading: Mitchell, Chapter 6 Murphy 2012, Chapter 3.5 Linear Regression, Cost Function, Gradient Descent     Reading: Barber, Chapter 14.1-14.2 Logistic Regression     Reading: Bishop, Chapter 10 Murphy 2012, Chapter 8 Regularization     Reading: Murphy 2022, Chapter 4.5, 13.5 Support Vector Machines     Reading: Murphy, Chapter 14.5,14.2 Barber, Chapter 17.5 Bishop, Chapter 7.1 Neural Networks     Reading: CIML, Chapter 10 Bishop, Chapter 7.1 Murhpy 2022, Chapter 13 Introduction Deep Learning and Convolutional Neural Networks     Reading: Murhpy 2022, Chapter 13,14 CS231n at Standford Un. Unsupervised Learning, K-Means Clustering     Reading: CIML, Chapter 15 Bishop, Chapter 9.1 Murhpy 2022, Chapter 21 Ensemble Learning: Bagging, Boosting     Reading: CIML, Chapter 13 Bishop, Chapter 14.1-3 Murhpy 2022, Chapter 18.2-5 Principal Component Analysis (PCA) Reading: CIML, Chapter 15 Bishop, Chapter 12.1 Markov Decision Process Reading: Russell, Chapter 17 Reinforcement Learning Reading: Russell, Chapter 21 Acknowledgements I thank to Prof. Ilyas Çiçekli and Prof. Erkut Erdem at Hacettepe University, and Prof. Eric Eaton at University of Pennsylvania for sharing their course slides publicly. Presentations on this page are mostly adapted from their slides. I also used some other public resources when constructing my course slides, I thank to all contributors.