The curriculum runs over 3 semesters (18 months) and consists of 14 modules: 10 basic and 4 advanced. You follow the basic modules during the first two semesters and the advanced modules in the final semester.

Along with your studies, you pursue a work-based learning for the company.

The 90 ECTS credits of this MSc are distributed as follows:

Mandatory modules

ECTS2
Repetition of Modulespring semester
Target AudienceStudents from semester 1
Description

This course covers Linear Algebra from basic matrix/vector operations to singular value decomposition and probabilities from fundamental basics to Markov chains and limit theorems, which are prerequires for most of the AI courses.

The course will be directed by examples and intuition rather than formalism. Python language will be used in examples and exercises. Octave (matlab) equivalent will also be available for the linear algebra part.

Although this course covers most of the basics, it is assumed students have some notion and background in linear algebra, probability and coding.

Labs will be application exercises (numeric or not) and exercises aiming at introducing aspects or notions that are not discussed in the course.

 

Lecturer

Ina Kodrasi
Théophile Gentilhomme

Assistants

Parvaneh Janbakhshi
Christine Marcel

ECTS4
Repetition of Modulespring semester
Target AudienceStudents from semester 1
Description

The course gives global knowledge in data structure and algorithms. It is organized in 5 parts:

1. Introduction

2. Data structures and algorithms

3. Practical use of data formats

4. Advanced algorithms

5. Computing tools

Lecturer

Olivier Bornet

Assistants

Christine Marcel
Philip Abbet
William Droz
Salim Kayal
Flavio Tarsetti

ECTS4
Repetition of Modulespring semester
Target AudienceStudents from semester 1

Lecturer

Michael Liebling

Assistants

Christine Marcel

ECTS4
Repetition of Modulespring semester
Target AudienceStudents from semester 1

Lecturer

Philip N. Garner
Ina Kodrasi

Assistants

Christine Marcel

ECTS2
Repetition of Moduleautumn semester
Target AudienceStudents from semester 2
Description

• AI and the Law

• AI and Data Protection

• AI and Ethics

• Reproducibility, What is it?

• Data Organization and Evaluation

• Version Control with git

• Code Sharing with GitLab

• Unit Testing and Continuous Integration

• Documentation and Reporting

• Packaging and Deployment

 

Lecturer

André Anjos
Portrait of Sébastien Marcel
Sébastien Marcel
Olivier Bornet

Assistants

Joël Dumoulin
Marie-Constance Landelle
Pavel Korshunov
Flavio Tarsetti
Christine Marcel
François Charlet

ECTS4
Repetition of Moduleautumn semester
Target AudienceStudents from semester 2
Description

• Linear regression

• Logistic Regression

• Decision Trees

• Boosting

• Multi-layer Perceptron

 

Lecturer

Portrait of Sébastien Marcel
Sébastien Marcel
André Anjos
Jean-Marc Odobez
Andre Freitas

Assistants

Anshul Gupta
Tiago de Freitas Pereira
Michael Villamizar
Rabeeh Karimi Mahabedi
Christine Marcel
Danick Panchard
Pavel Korshunov
Anjith George
Marco Valentino

ECTS4
Repetition of Moduleautumn semester
Target AudienceStudents from semester 2
Description

This class covers basic concepts in image and video processing as well as computer vision. Topics include image formation and sampling, image transforms, image enhancement, and image and video compression. Computer vision topics include points of interest, optical flow, and camera calibration.

• Introduction to Digital Image processing (imaging types and

formats, applications)

• Point operations, image histograms

• Spatial Filtering and convolutions

• Edge detection

• 2D Fourier Transforms and representation of images, sampling, and image resizing (low pass filters, pyramids)

• Color images and color transformations

• Interest points (detection, representation, invariance, matching, RANSAC...)

• Calibration

• Optical Flow

Lecturer

Michael Liebling
Jean-Marc Odobez

Assistants

Michael Villamizar
Christine Marcel

ECTS4
Repetition of Moduleautumn semester
Target AudienceStudents from semester 2
Description

• Dimensionality Reduction and Clustering

• Kernel Methods and Support Vector Machines

• Graphical Models

• Exact and Approximate Inference in Bayesian Networks

• Probability Distribution Modelling

Lecturer

Portrait of Sébastien Marcel
Sébastien Marcel
André Anjos
James Henderson
Jean-Marc Odobez

Assistants

Samy Tafasca
Michael Villamizar
Rabeeh Karimi Mahabedi
Andreas Marfurt
Danick Panchard
Christine Marcel
Tiago de Freitas Pereira
Anjith George

ECTS4
Repetition of Moduleautumn semester
Target AudienceStudents from semester 2
Description

This course will introduce the students the fundamentals of speech processing and provide them with the key formalisms, models and algorithms to implement speech processing applications such as, speech recognition, speech synthesis, paralinguistic speech processing, multichannel speech processing.

 

Course content

 

Introduction

why speech processing? speech production, speech perception, basic

phonetics

 

Speech signal analysis

Sampling, Quantization, Time domain processing, Frequency domain

processing, linear prediction, cepstrum, speech coding

Practical: Speech signal analysis in Octave and Praat

 

Machine learning for speech processing

Static classification, Sequence classification, Regression

Practical: Statistical pattern recognition, Hidden Markov models in Octave

 

Automatic speech recognition

Dynamic programming, Instance-based speech recognition, Hidden

Markov model-based speech recognition, Evaluation measures

Practical: Kaldi tutorial

 

Text-to-speech synthesis

Concatenative speech synthesis, Statistical parametric speech synthesis, Evaluation measures

Practical: Grapheme-to-phoneme conversion, HMM-based speech synthesis

 

Paralinguistics speech processing

Emotion, gender, accent, pathological speech assessment, Evaluation

measures

Practical: OpenSMILE tutorial

Lecturer

Mathew Magimai Doss

Assistants

Christine Marcel
Prasad Ravi
Julian Fritsch
Pavankumar S. Dubagunta
Enno Hermann

ECTS4
Repetition of Modulespring semester
Target AudienceStudents from semester 3

Lecturer

Olivier Canévet

Assistants

Christine Marcel
Alexandre Nanchen

ECTS10
Repetition of Modulespring semester
Target AudienceStudents from semester 1

Lecturer

Olivier Bornet
Joël Dumoulin

Assistants

Christine Marcel

ECTS30
Repetition of Moduleautumn semester
Target AudienceStudents from semesters 1 and 2
Description

The aim of Module P02-AI Project(s) development is to develop the project(s) the student defines in Module P01 – AI Company strategy and Project(s) definition.

Lecturer

Joël Dumoulin
Olivier Bornet

Assistants

Christine Marcel
Jérôme Kämpf
Raphaëlle Luisier

Do you have any questions?

Our Student Managers will be glad to help you!
    Portrait of Jean-Paul Droz
    Portrait of Federico Elia
    Portrait of Marina Mayor
    Portrait of Céline Pellissier
    Portrait of Christelle Perruchoud
    Portrait of Sarah Taurian Alves
    Portrait Désirée Abgottspon
    Portait of Sinah Amherd
    Portrait of Alexandra Steiner
    Portrait of Evelyn Winter
    Portrait of Irisea Volken