DTAI

  • Increase font size
  • Default font size
  • Decrease font size
DTAI News ML news
ML news

Automatic Discovery for Research in Machine Learning (Dr. Francis Maes)

Wednesday May 2, 2012, at 10h00 in Celestijnenlaan 200A (room 200A.05.001)

Automatic Discovery for Research in Machine Learning
by Dr. Francis Maes

Machine learning research aims at conceiving and analyzing algorithms to solve specific data-related problems. Researchers in this field typically use a trial-and-error approach to reach these goals, in which algorithms are progressively improved on the basis of empirical evidence and/or theoretical analysis. This research process has some important drawbacks: it is inherently biased towards solutions that seem intuitive to humans, it is time-consuming and it is rarely reproducible. In this talk, I will defend the approach which consists in formalizing this trial-and-error approach and in using automatic discovery tools to discover new high-performance algorithms. The talk is structured in two main parts. In the first one, I will formalize the search for high-performance algorithms as a multi-armed bandit (MAB) problem and illustrate the MAB approach on three different problems: discovering control policies, discovering MAB algorithms and discovering reinforcement learning algorithms. In a second time, I will consider the problem of exploring large tree-structured expression spaces and propose some alternatives to Genetic Programming for this task. The proposed approaches formalizes the problem as a "one-player game" and relies on Monte-Carlo search techniques to solve this game. I will illustrate it on symbolic regression and on automatic feature generation. Through these numerous examples, my hope is to show that automatic discovery tools are extremely relevant to research in machine learning and that these tools are a key to quickly unlock several new research avenues.

 

ICPRAM12 Best Paper Award for Laura Antanas

Laura Antanas and colleagues have won the best paper award at the first International Conference on Pattern Recognition Applications and Methods (ICPRAM) for their paper

A RELATIONAL DISTANCE-BASED FRAMEWORK FOR HIERARCHICAL IMAGE UNDERSTANDING
Laura Antanas, Martijn van Otterlo, José Oramas, Tinne Tuytelaars and Luc De Raedt

 

ILP11 Best Paper Award for Joris Renkens

Joris Renkens and colleagues has won the ILP 2011 Student Theory Prize ("Turing Theory Prize" funded by MLJ) for their paper:

 

"k-Optimal: A Novel Approximative Inference Algorithm for ProbLog"
Joris Renkens, Guy Van Den Broeck, Siegfried Nijssen

 

Seminar: Image Data Analysis in H.sapiens and C.elegans by Dr. Alexander K. Seewald

Fri, Jan 20, 2012, 15h--16h

Talk "Image Data Analysis in H.sapiens and C.elegans"
by Dr. Alexander K. Seewald
200A.05.001

Abstract:
In the past three years, we have collaborated with the Univ. of Colorado, Boulder, USA, and the Institute for Medical Pathology at the Medical University, Vienna. The focus of our research was on developing image analysis systems using state-of-the-art techniques, including machine learning techniques which have been previously used to recognize faces. We have developed robust preprocessing methods (stitching, illumination correction, erythrocyte removal), segmentation algorithms and task-specific evaluation algorithms based on ground-truth data provided by our biological researcher partners. We have analyzed three different types of tissue: human osteoclast in culture, human placental tissue, and living transgenic C. elegans specimen.

We will close with thoughts on the potential uses of image data analysis, what is and is not yet feasible, and how biological researchers should be expected to help in the building of state-of-the-art systems.

Last Updated on Wednesday, 18 January 2012 10:08
 

Seminar: Model-based Dependability Analysis & System Architecture Optimisation Using HiP-HOPS, Prof. Papadopoulos (University of Hull)

On December 8th, the DTAI research group organizes a three-part seminar about Safety, Diagnostics and SRL. This takes place in room 200A.05.152 and starts at 10h00.

Program

  • 10h00: Machine Learning for Diagnostics
    Wannes Meert, DTAI research group, KULeuven
  • 10h30: Overview of FMTC activities
    Joe De Waele, FMTC
  • 11h00: Model-based Dependability Analysis & System Architecture Optimisation Using HiP-HOPS.
    Dr Yiannis Papadopoulos, Professor of Computer Science, Department of Computer Science, University of Hull
  • 12h00: end

Last Updated on Wednesday, 30 November 2011 12:09 Read more...
 
  • «
  •  Start 
  •  Prev 
  •  1 
  •  2 
  •  3 
  •  4 
  •  5 
  •  6 
  •  7 
  •  8 
  •  9 
  •  10 
  •  Next 
  •  End 
  • »


Page 1 of 10