Introduction to machine learning

Welcome!

This course aims to introduce the fundamental principles and methods of machine learning from both a theoretical perspective, via lectures, and a practical one, via pen-and-paper and coding exercise sessions. We will study different techniques covering both supervised and unsupervised learning.

Content 

Introduction

• ML Basics
• K Nearest Neighbors
• K Means

Linear ML 

•  Linear Regression
•  Logistic Regression
•  Max Margin Classifiers

Nonlinear ML

•  AdaBoost
•  Polynomial Support Vector Machines
•  Kernel Methods
•  Artificial Neural Networks

Organization 

The lectures will be taught in RLC Forum during the official class hours, i.e., Tuesdays 8:00-10:00. They will also be recorded, and the videos will be posted on SWITCHtube:
https://mediaspace.epfl.ch/channel/channelid/69489


The pen-and-paper exercise sessions will occur in rooms INF019, INJ218, INM10, ELD020, INM202 during the official schedule, i.e., Tuesdays 17:00-19:00.
The coding exercise sessions will occur in rooms BS150, BS160, BS260, BS270, GRB330 during the official schedule, i.e., Fridays 15:00-17:00.
For organizational purposes, please register your name to one room at the following link:
https://docs.google.com/spreadsheets/d/1r4qF_P435HNaYOsgYgOlhhyts-OsFlWHopcICb-Jvrw/edit?usp=sharing

Assessment method

20% of the final grade: Two milestones (10% each) for the team coding project.
80% of the final grade: Final exam with multiple choice and open-ended questions.

Lecturer 

Pascal Fua
Office: BC 310
E-Mail: pascal.fua@epfl.ch

Teaching Assistants

• Saqib Javed
• Haoqi Wang
• Shuangqi Li
• Wei Zhen
• Robin Zbinden
• Tianzong Zhang
• Youssef Allouah
  
• Megh Shukla
• Fares Fawzi
• Yihong Chen
• Lucas Louis Gruaz
• Liangze Jiang

Student Assistants

• Antoni Jubés Monforte
• Bojan Lazarevski
• Tamar Alphaidze 
• Julien Pierre Barozet - Golbery 
• David Farah
• Matea Tashkovska
• Anunay Yadav 
• Iskandar Ghobril
• Matya Aydin
• Mahdi Atallah
  
  

Bibliography 

• Christopher M. Bishop, Pattern Recognition and Machine Learning, Springer, 2006