ORBi: Marcos Alvarez Alejandro - Supervised learning to tune simulated annealing for in silico protein structure prediction

Reference : Supervised learning to tune simulated annealing for in silico protein structure prediction


	Document type :	Scientific congresses and symposiums : Paper published in a book
	Discipline(s) :	Engineering, computing & technology : Computer science
	To cite this reference:	http://hdl.handle.net/2268/117699

Title :	Supervised learning to tune simulated annealing for in silico protein structure prediction
Language :	English
Author, co-author :	Marcos Alvarez, Alejandro [Université de Liège - ULg > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Systèmes et modélisation >]
	Maes, Francis [Université de Liège - ULg > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Systèmes et modélisation >]
	Wehenkel, Louis [Université de Liège - ULg > Dép. d'électric., électron. et informat. (Inst.Montefiore) > Systèmes et modélisation >]
Publication date :	25-Apr-2012
Main document title :	ESANN 2012 proceedings, 20th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning
Editor :	Verleysen, Michel
Publisher :	Ciaco
Pages :	49-54
Peer reviewed :	Yes
On invitation :	No
Audience :	International
ISBN :	978-2-87419-047-6
City :	Louvain-la-Neuve
Country :	Belgium
Event name :	ESANN 2012, 20th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning
Event date :	from 25-04-2012 to 27-04-2012
Event organizer :	UCL, Université Catholique de Louvain, Louvain-la-Neuve
	KULeuven, Katholiek Universiteit Leuven, Leuven
Event place (city) :	Bruges
Event country :	Belgium
Keywords :	[en] Optimization ; Machine learning ; Simulated annealing ; Protein ; Structure prediction
Abstract :	[en] Simulated annealing is a widely used stochastic optimization algorithm whose efficiency essentially depends on the proposal distribu- tion used to generate the next search state at each step. We propose to adapt this distribution to a family of parametric optimization problems by using supervised machine learning on a sample of search states derived from a set of typical runs of the algorithm over this family. We apply this idea in the context of in silico protein structure prediction.
Research units :	Systèmes et Modélisation, GIGA-Research
Funders :	Fonds de la Recherche Scientifique (Communauté française de Belgique) - F.R.S.-FNRS
Target :	Researchers ; Professionals ; Students
Permalink :	http://hdl.handle.net/2268/117699

File(s) associated to this reference

Fulltext file(s):

	File	Commentary	Version	Size	Access
Open access	esann_2012.pdf		Author preprint	121.65 kB	View/Open

All documents in ORBi are protected by a user license.

Dspace v1.5