Antoine Cornuéjols (AgroParisTech)
||Professeur / Full Professor
Dept. MMIP (Modélisation Mathématique, Informatique et Physique)
16, rue Claude Bernard
75005 Paris Cedex (France)
Tel : +33 (0)1-44-08-72-29
email : antoine.cornuejols [at] agroparistech.fr
My fields of research
lie in Machine
and, now somewhat remotedly, Cognitive Science. I am specially
interested in the following topics :
- Full Professor in Computer Science at AgroParisTech,
head of the "Modélisation Mathématique, Informatique
et Physique" (MMIP) department at AgroParisTech,
- head of
the LINK (Learning and INtegration of Knowledge) research team within the UMR-MIA 518 AgroParisTech-INRA research unit.
Fundamentals of learning (more
The geometry of learning
- What is the space of programs when the change
operator is learning from examples ?
kind of dot products can yield negative values (as opposed to the
mutual information which is not fit for learning) ?
is a proper metrics ?
does order sensitivity in learning relate to curved space ?
- How to best order a data sequence
for a specific goal ?
- Which data should be presented
- In which order ?
- At which speed ?
learning (in a stationary environment)
- With covariate shift
Transfer of information
- Analogical reasoning
- Which foundations for analogical
- Which links with inductive reasoning
- Learning of new conceptual domains
articulations with known domains allow to learn a new conceptual
- How a conceptual domain in the
learning come to get integrated with other conceptual domains ?
- What are the effects of limited transmission
bandwith in a collection of learning agents ?
Phase transition in inductive learning
- What is the influence of language on learning
new knowledge ?
- How is inductive supervised learning affected
by the description language ?
- What explanation for phase transitions
in supervised learning ?
- How to alleviate these with changes of
representation language ?
Application oriented methodological developments
Applications in data mining
analysis in changing environments
of the memory in on-line learning
detection in the dynamical recognition of a moving kidney
analysisin a risk assessment task
of parts of texts related to a risk assessement qualification
assessement of uncertainty in parts of text
from positive instances only
of the false positive rate
of abstraction and change of granularity in data mining methods
of genomics and microarray data
- Combination of
weak selection methods
- Active methods
for feature selection
of cardiovascular accidents (prediction of)
for learning in the presence of imbalanced data sets and asymetrical