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
Zoom Lecture Link: https://epfl.zoom.us/j/88600635898
Meeting ID: 88600635898
Teaching Assistants
- Sena Kiciroglu
- Jan Bednarik
- Edoardo Remelli
- Okan Altingovde
- Nikita Durasov
Student Assistants
- Robin Zbinden
- Olivier Lam
- Stanislas Jouven
Organization
The lectures will be taught live, during the official class hours, i.e., Tuesdays 8:15-10:00. They will be streamed online via zoom and recorded. The videos will be posted on SWITCHtube (link to the channel: https://tube.switch.ch/channels/97cd11b0 ). The zoom link to the lectures is: https://epfl.zoom.us/j/88600635898
The exercise sessions will be held weekly on Tuesdays 10:15-12:00 and will consist of implementing the machine learning methods learned in class. The TAs will be present online via zoom to answer questions. The zoom link for the exercise sessions is: https://epfl.zoom.us/j/99022101297Office Hours
If you have any questions please post them in the discussion forum and we will answer you.
Final Exam
The final exam, if possible, will be held on-campus. It will be closed book and will represent 100% of your final grade. You will be allowed to have one A4 sheet (both sides) of handwritten notes.
Mock Exam
We will give a mock exam in the middle of the semester so that you have an idea of what to expect for the final.
- Sena Kiciroglu
-
23.02.2021 Lecture 1: Introduction, Digital Images, K-Nearest Neighbors
Exercise Session: Introduction to Python02.03.2021 Lecture 2: K-Nearest Neighbors, Python Primer
Exercise Session: Introduction to NumPy09.03.2021 Lecture 3: K-Means Clustering. Linear Classification
Exercise Session: K-Nearest Neighbors16.03.2021 Lecture 4: Linear Classification, Max-Margin Classifiers
Exercise Session: K-Means Clustering23.03.2021 Lecture 5: Optimization Basics
Exercise Session: Logistic Regression30.03.2021 Lecture 6: Adaboost and Support Vector Machines
Exercise Session: Linear SVM06.04.2021 Easter Break 13.04.2021 Lecture 7: Support Vector Machines
Exercise Session: Kernel SVM20.04.2021 Lecture 8: Multi Layer Perceptron
Exercise Session: MLP27.04.2021 Lecture 9: Multi Layer Perceptron (Part 2)
Exercise Session: Mock Exam04.05.2021 Lecture 10: CNN (Part 1)
Exercise Session: CNN (part 1)11.05.2021 Lecture 11: CNN (Part 2)
Exercise Session: CNN (part 2 and 3)18.05.2021 Lecture 12: Linear Dimensionality Reduction
Exercise Session: Linear dimensionality reduction (PCA, LDA)25.05.2021 Lecture 13: Non-linear Dimensionality Reduction
Exercise Session: Non-linear Dimensionality Reduction01.06.2021 Lecture 14: Review Session
Exercise Session: Review -
C.M. Bishop, Pattern Recognition and Machine Learning, Springer, 2006.
M. Welling, A First Encounter with Machine Learning, 2011
