View Item

Domain Machine Learning-Robotics
Domain - extra
Year 2014
Starting 01/10/2014
Status Open
Subject An empirical approach to machine learning: algorithm selection, hyperparameter optimization, and automatic principle design
Thesis advisor KÉGL Balázs
Co-advisors Michele Sebag
Laboratory EXT
Abstract In this thesis project we propose to apply the scientific method to machine learning. We will explore two lines of research. In the first we will build on recent work applying modern experimental design for algorithm selection and hyperparameter tuning. The main thrust of this sub-project is the multi-problem approach: we will explore the interaction between methods (and hyperparameters) and data sets to find out whether and to what extent experience can be generalized across data sets. The output of this project is a toolbox for practitioners and a stockpile of knowledge on what algorithm works on what (kind of) data sets. This second output will feed into the second line of research: we will ask the question of \emph{why} certain methods work on certain data sets. We will study algorithms as natural phenomena, form hypotheses, design and evaluate experiments, and carry out measurements that could validate or refute our hypotheses.
Work program
Extra information
Details Download empirical.pdf
Expected funding Institutional funding
Status of funding Expected
Candidates Sourava Prasad Mishra
user balazs.kegl
Created Sunday 18 of May, 2014 08:49:34 CEST
LastModif Sunday 18 of May, 2014 08:57:10 CEST
Attachments (1)


Downloadempirical.pdf18 May 2014 08:57158988.42 Kb

The original document is available at