0;136;0c Applied Machine Learning | LASA
english only
EPFL > STI > IMT > LASA > Teaching > Applied Machine Learning
LASA MENU
Home
Research
Publications
Teaching
People
Arriving to LASA
Videos / Photos
Press & News

GitHub Repository
Older Source Codes
The Blog
Intranet

Prospective Students
TEACHING INDEX
Teaching
Student Projects
Former Projects
Robot Contests

APPLIED MACHINE LEARNING

MSc Course

   Objectives  

 

Real-world engineering applications must cope with a large dataset of dynamic variables, which cannot be well approximated by classical or deterministic models. This course gives an overview of a number of alternative methods from Machine Learning for the analysis of non-linear, highly noisy and multidimensional data.

Because machine Learning can only be understood through practice, by using the algorithms, the course is accompanied with practicals during which students test a variety of machine learning algorithm with real world data .
http://mldemos.epfl.ch/

   Instructors  
Prof. Aude Billard  

LASA Laboratory
Swiss Federal Institute of Technology - EPFL
CH-1015 Lausanne, Switzerland

email: aude.billard@epfl.ch

Office Hours: Monday, 14:00 to 16:00, by appointment. (room ME.A3.393)
Tel: +41 (21) 693.54.64
fax: +41 (21) 693.78.50

Assistants


Laura Cohen
email: laura.cohen@epfl.ch
Room: ME.A3.454 
Tel: 021 693 29 19

Murali Karnam
email: murali.karnam@epfl.ch
Room: ME.A3.395 
Tel: 021 693 38 55

Denys Lamotte
email: denys.lamotte>@epfl.ch
Room: ME.A3.474 
Tel: 021 693 54 63

   Time and Location  
09:15-13:00 (08:15-10:00 and 11:15-13:00 for the practicals)
Class takes place in room ELA1 and CO4-CO6 for the whole semester. Class alternates between Lectures and Exercises. Lectures + exercises take place in the same room ELA1, and practical sessions on computer in CO4-CO6. Please pay attention to the hours which are different if the class is a lecture or a practical.  

Grade is divided as follows: 25% In-class assessment + 75% Written Exam

   Moodle Page  

The Moodle page of the course is available by clicking on the link below.

Moodle

   Lecture Notes  

The Lecture Notes of this course can be download by clicking on the link below.

Lectures Notes

   MachineLearningDemos Software  

A suite of algorithms has been implemented for you in the form of a user-friendly program that allows you to play with data and to study how each method performs in different tasks of classification, clustering and regression. A number of examples in the lecture notes have been generated by this software, and are available as examples in the package below (refer to the Lecture Notes to know which examples are available). The software runs on Windows and requires the .Net Framework 3.0 (which should be installed in your machine already, but if it isn't, pick it up here).

Download MLDemos (click)

MLDemos (DBSCAN for TP2)

Interface (TP4)

   Group Doodle  

Assignments throughout the course will be carried out in teams of two. Once you have found your team mate sign your selfs up on the following Doodle (click). If you are not taking the course for credit don't team up with somebody who is. Then once you have chosen your team number, please go to this Doodle (Click) to choose between a written report or an oral presentation. (Places for oral presentation are limited to 30 groups). Indicate your team number in the field name.

   Practicals  

The description of the work which has to be done during the practice sessions can be found here (click).
In order to help you for both the report and the presentation we also give you two templates you will have to complete with your analysis :
- Template for the presentation
- Template for the report (pdf) (latex)

   Timetable
<

Date INFO Location Slides of Lectures Exercises/Practicals Template Solutions

23/09/16

Doodle for exercises in lectures

ELA1 INTRO
REDUCTION OF DIMENSIONALITY
Principal Component Analysis
Exercises
Solutions

30/09/16

08:15-10:00 ; 11:15-13:00 CO4-CO6

Practical 1 : PCA

Assignment I

Dataset of Part 1

07/10/16

Deadline to fill in the doodles (one for the teams and one to choose between report or presentation) by 18:00 ELA1 CLUSTERING
K-Means, Soft K-Means, DBSCAN
Metrics to evaluate clustering
Exercises
Solutions
14/10/16 08:15-10:00 ; 11:15-13:00 CO4-CO6

Practical 2 : Clustering

Assignment II

21/10/16

ELA1

Continuous Distributions
(EM tutorial, EM convergence)
Exercises
Solutions
28/10/16   ELA1

CLASSIFICATION
Classifiers: GMM + Bayes

Exercises
Solutions
04/11/16      No course at this date

11/11/16

 

ELA1

CLASSIFICATION
Support Vector Machine
Complement Convex Optimization

  Exercises


Solutions

18/11/16 08:15-10:00 ; 11:15-13:00 CO4-CO6

Practical 3 : Classification

Assignment III

25/11/16   ELA1

REGRESSION
Linear + weighted regression - SVR

Exercises

Solutions

02/12/16


ELA1

REGRESSION
GMR

ExercisesSolutions
09/12/16
08:15-10:00 ; 11:15-13:00 CO4-CO6  Practical 4 : Regression
Assignment IV
16/12/16 Deadline to submit the written report for those who chose it by midnight
CO4-CO6

Oral Presentations of Practicals (See email for timetable)
This presentation counts for 25% of the total grade

23/12/16
ELA1  

Overview of the class

Overview
20/01/2017
08:15-11:15
CO1, CO2  

EXAM
(written, closed books, 3 hours)


   Textbooks/Further Readings  
Here are books in which you can find a complete coverage of some of the techniques seen in class.


Last update: 9/09/2016