Welcome to TAO Web site
TAO is the mixed INRIA Saclay
— CNRS — LRI, Université Paris-Sud research group interested in the interplay of Machine Learning (A for Apprentissage) and Optimization (O). The two pillars of TAO's research are:
- Machine Learning for Cognitive Systems See Pascal-2, Pattern Analysis, Statistical Modelling, Computational Learning, FP7 NoE IST
- Evolutionary Computation for Complex Systems
- What is this all about ...
- What is specific in TAO
- National links: Digiteo and Apprenteo; AO and Statistical Physics
- Past: co-chair European Conference on Machine Learning / Principles and Practice of Data Mining — 2010
News
Internal:- TAO 2011 activity report is available
- Workshops at ECAI 2012
- DAEYAHSP Winner of the Seventh International Planning Competition (Deterministic Temporal Satisficing track) at ICAPS 2011 - see project page
- New successes for MoGo (click here for details):
- 3 Gold Medals at TAAI Computer Games Tournament (9x9, 13x13, 19x19).
- The MoGo team received the Chess Base Award 2009 (together with INRIA team SEQUEL in Lille) for its contribution to Computer Games.
- 3 Gold Medals at TAAI Computer Games Tournament
- New Book about New Horizons in Evolutionary Robotics, co-edited by Nicolas Bredeche (with Stéphane Doncieux and Jean-Baptiste Mouret). Springer link
- New Book on Theory of Randomized Search Heuristics - Foundations and Recent Developments edited by Anne Auger and Benjamin Doerr
- Best Paper Award at the ES-EP track of ACM GECCO 2010
- Silver Medal at the ACM GECCO 2010 Humies Awards for our work on AI Planning. See the most prominent paper, or the complete related bibliography.
- Women in ML
National
- About CS courses at LRI
- New Book about Brain-Computer Interfaces from a TAO member (Cédric Gouy-Pailler) Amazon.fr link Amazon.com link (In french, May 2010)
- Chinese National Award for Outstanding Abroad PhD awarded to Xiangliang Zhang for her PhD on Data Clustering and Streaming for Autonomic Grids, supervised by Michele Sebag and Cecile Germain. See more...
See also Old News
Research
The main on-going research directions/projects are:
- Autonomic Computing - how to make a gigantic distributed computing system self-aware, self-healing, self-optimizing, self-?... (more...)
- Project: Grid Observatory, Work Package in EGEE-III.
- Crossing the Chasm. Why so many good algorithms don't make it outside of the research labs ? How to tune them is part of the answer... (more...)
- Automatic Parameter Tuning, Microsoft Research / INRIA Joint Lab.
- Automatic Parameter Tuning, Microsoft Research / INRIA Joint Lab
- Developmental Design, Swarm Robotics and other Complex Systems. When what you optimize is the process leading to the result (this is ''embryogenesis'). more...
- Project: SYMBRION Integrated Project, FP7.
- Project: SYMBRION
- Multi-Disciplinary and Continuous Optimization; dealing with computationally expensive, noisy, mixed, structured, objective functions. (more ...)
- Projects OMD and OMD2
- Projects OMD
- Optimal decision making under uncertainty - best illustrated by the computer-Go program MoGo? - first program to ever win over a professional Go player. (more...)
- Reservoir Computing. How can large random structures be more efficient than carefully crafted ones (e.g. in Neural Networks) ? (more...)