Aude Billard

photo placeholder image

Full Professor

aude.billard@epfl.ch +41 21 693 54 64 http://lasa.epfl.ch/

Citizenship: swiss

EPFL STI IMT LASA
ME A3 393 (Bâtiment ME)
Station 9
CH-1015 Lausanne

Web site:  Web site:  https://lasa.epfl.ch/

EPFL STI IGM-GE
MED 0 1726 (Bâtiment MED)
Station 9
CH-1015 Lausanne

vCard
Administrative data

Fields of expertise

Machine Learning 
Robotics 
Mechatronics 
Dynamical Systems
Computational Neuroscience

Professional course

Full Professor

EPFL

2013

Associated Professor with Tenure

EPFL

2006-2012

Assistant Professor

EPFL

2002-2006

Assistant Professor

University of Southern California

2000-2002


Education

PhD

Artificial Intelligence

University of Edinburgh

1998

MSc

Knowledge-Based Systems

University of Edinburgh

1996

BSc & MSc

Physics

EPFL

1995

Teaching & PhD

Teaching

Microengineering

Mechanical Engineering

PhD Programs

Doctoral Program in Electrical Engineering

Doctoral program in robotics, control, and intelligent systems

Doctoral Program in Neuroscience

Doctoral Program Digital Humanities

Doctoral Program in Biotechnology and Bioengineering

Doctoral Program in Learning Sciences

Courses

Machine learning programming

This programming class complements courses on machine learning given in the school. It offers students the possibility to  understand some machine learning algorithms in depth by programming them and testing them rigorously. Students will be offered a choice of methods to program. Programming can be done in matlab or C/C . Proper evaluation of machine learning will be stressed out. Students wi

Robotics practicals

The goal of this lab series is to practice the various theoretical frameworks acquired in the courses on a variety of robots, ranging from industrial robots to autonomous mobile robots, to robotic devices, all the way to interactive robots.

Applied machine learning

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 . The courses uses matlab libraries for machine learning, as well as the MLDEMOS

Learning and adaptive control for robots

To cope with constant and unexpected changes in their environment, robots need to adapt their paths rapidly and appropriately without endangering humans. this course presents method to react within millisecunds.

Advanced machine learning

  • Introduction to the major mathematical principles of Machine Learning
  • Structure Discovery: spectral and kernel methods, kernel PCA.CCA, kernel K-means, Spectral Clustering, Manifold Learning, Support Vector Clustering
  • Advanced Classification and Nonlinear Regression Methods: nu-SVM/SVR, Relevance Vector Machine, Transductive SVM, Gaussian Processes
  • Stochastic M