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/

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


Awards

Intel Corporation

SNSF Professeur Boursier

The Outstanding Young Person in Science and Innovation

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

Courses

Machine learning programming

This is a practice-based course, where students program algorithms in machine learning and evaluate the performance of the algorithm thoroughly using real-world dataset.

Robotics practicals

The practicals can include the following topics:

  • Teaching Robots to Accomplish a Manipulation Task
  • Experimenting with haptic interfaces
  • Controlling a serial robot ABB IRB 120
  • Control of the Micro Delta Direct Drive robot
  • LiniX, linear axis, assembly and control

    Applied machine learning

    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 methods from Machine Learning for the analysis of non-linear, highly noisy and multi dimensional data

    Learning and adaptative 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