Introduction to machine learning (BA4)
Weekly outline
-
Welcome to the machine learning class!
Machine learning and data analysis are becoming increasingly central in many sciences and applications. In this course, fundamental principles and methods of machine learning will be introduced, analyzed and practically implemented using Python.
Instructor
Prof. Pascal Fua
Computer Vision Laboratory (CVLAB)
Office: BC 310
E-mail: pascal.fua@epfl.ch
Teaching Assistants
- Nicolas Talabot (nicolas.talabot@epfl.ch)
- Alexandre de Skowronski (alexandre.deskowronski@epfl.ch)
- Nikita Durasov (nikita.durasov@epfl.ch)
- Ren Li (ren.li@epfl.ch)
- Saqib Javed (saqib.javed@epfl.ch)
- Tianzong Zhang (tianzong.zhang@epfl.ch)
Student Assistants
- Christelle Lam
- Eugène Bergeron
- Paul Teiletche
- Aitor Ganuza Izagirre
Organization
The lectures will be taught live, during the official class hours, i.e., Tuesdays 8:15-10:00 in CM3.
The class has a SWITCHtube channel where we have the links of the 2020/2021 lectures (link to the channel: https://mediaspace.epfl.ch/channel/CS-233%28b%29+Introduction+to+machine+learning+%28BA4%29/29366 ). The content of the lectures will be similar, but there may be changes so we recommend for you to attend the lectures in person.
The exercise sessions will be held in-person weekly in CE1100, CE1101, CE1103 on Tuesdays 10:15-12:00 and will consist of implementing the machine learning methods learned in class. The TAs and SAs will be present to answer questions.CE1100: Students with last names starting with A - F
CE1101: Students with last names starting with G - Matthey-Doret
CE1103: Students with last names starting with Mellouk - Z
Student Forum
If you have any questions please post them in the student forum and we will answer you.
Project
We will organise a small project in teams of 3, worth 20% of your final grade. There will be two milestones, each worth 10% of your final grade, at the end of week 8 and 14.
Final Exam
The final exam will be held on-campus. It will be closed book and will count for 80% of your final grade. The exam will consists in single-choice and multiple-choice questions (SCQ/MCQ), and some open-ended questions. You will be allowed to have one A4 sheet (both sides) of handwritten notes. The exam will take place on the 26 June 2023, at 15:15 (2 hours).
-
21.02.2023 Lecture 1: Introduction, Digital Images, K-Nearest Neighbors
Exercise Session: Introduction to Python28.02.2023 Lecture 2: K-Nearest Neighbors, K-Means Clustering
Exercise Session: Introduction to NumPy07.03.2023 Lecture 3: Clustering, Linear Regression
Exercise Session: K-Nearest Neighbors14.03.2023 Lecture 4: Linear Classification, Max-Margin Classifiers
Exercise Session: K-Means Clustering21.03.2023 Lecture 5: Optimization Basics
Exercise Session: Logistic Regression28.03.2023 Lecture 6: Adaboost and Support Vector Machines
Exercise Session: Project MS104.04.2023 Lecture 7: Support Vector Machines
Exercise Session: SVM11.04.2023 Easter Break 18.04.2023 Lecture 8: Multi Layer Perceptron
Exercise Session: Project MS125.04.2023 Lecture 9: Multi Layer Perceptron (Part 2)
Exercise Session: MLP02.05.2023 Lecture 10: CNN (Part 1)
Exercise Session: CNN (part 1)09.05.2023 Lecture 11: CNN (Part 2)
Exercise Session: UNet16.05.2023 Lecture 12: Linear Dimensionality Reduction
Exercise Session: Project MS223.05.2023 Lecture 13: Non-linear Dimensionality Reduction
Exercise Session: Dimensionality Reduction30.05.2023 Lecture 14: Review Session
Exercise Session: Project MS2 -
C.M. Bishop, Pattern Recognition and Machine Learning, Springer, 2006.
M. Welling, A First Encounter with Machine Learning, 2011
-
-
-
-
-
-
Abbassi - Jaouen
-
Jordan - Pantalos
-
Peiry - Zuber
-
