Loading...
 
[Show/Hide Left Column]

Sujets Help

View Item

Domain Machine Learning-Robotics
Domain - extra
Year 2010
Starting Oct. 2010
Status Open
Subject Deep Neural Nets: From Curriculum to Multi-Task Learning
Thesis advisor SEBAG Michèle
Co-advisors
Laboratory LRI A&O
Collaborations
Abstract Deep Neural Networks combine unsupervised and supervised learning.
The order of examples considered to train the DNN has been shown to have a significant influence on the performances, leading to the so-called Curriculum Learning
approach.

This PhD will investigate the relations between Curriculum Learning and Multi-Task Learning
Context see http://www.lri.fr/~sebag/Theses/Sujet_These_Deep.pdf
Objectives
Work program
Extra information
Prerequisite
Details
Expected funding Institutional funding
Status of funding Expected
Candidates Pierre Allegraud
user michele-martine.sebag
Created Monday 21 of June, 2010 09:58:34 CEST
LastModif Monday 21 of June, 2010 09:58:34 CEST


Ecole Doctorale Informatique Paris-Sud


Directrice
Nicole Bidoit
Assistante
Stéphanie Druetta
Conseiller aux thèses
Dominique Gouyou-Beauchamps

ED 427 - Université Paris-Sud
UFR Sciences Orsay
Bat 650 - aile nord - 417
Tel : 01 69 15 63 19
Fax : 01 69 15 63 87
courriel: ed-info at lri.fr