Meta-learning Workshop

In Conjunction with the

20th International Joint Conference on Neural Networks

Workshop Program

Introduction

This workshop is about meta-learning. One underlying goal of meta-learning is the understanding of the interaction between the mechanism of learning and the concrete contexts in which that mechanism is applicable. Meta-learning differs from base-learning in the scope of the level of adaptation. Whereas learning at the base-level focuses on accumulating experience on a specific learning task (e.g., credit rating, medical diagnosis, mine-rock discrimination, fraud detection, etc.), learning at the meta-level is concerned with accumulating experience on the performance of multiple applications of a learning system. This, in turn, may assist in such applications as model selection and transfer learning.

Over the past decade, much work has been done in this area, scattered across mostly traditional machine learning journals and conferences. We feel there is added value in bringing interested researchers, especially those from the neural network community, together in a workshop to assess the state-of-the-art, see where we are going and provide new impetus to the field.

Detailed Program

7:00 PM - Welcome and Introduction
7:10 PM - Keynote Address: Bootstrapped Learning and Deliberative Meta Learning, Dan Oblinger, DARPA, USA
8:10 PM - Break
8:25 PM - Contributed Paper: Meta-learning as Scheme-based Search with Complexity Control, Krzysztof Grabczewski and Norbert Jankowski, Nicolaus Copernicus University, Poland
8:45 PM - Invited Talk: Bridging the Gap between Data Mining and Decision Support, Michel Charest, Universty of Quebec at Trois-Rivieres, Canada
9:15 PM - Break
9:30 PM - Contributed Paper: No-Free-Lunch and Bayesian Optimality, James Carroll and Kevin Seppi, Brigham Young University, USA
9:50 PM - Invited Talk: Generalising Meta-learning Concepts: from Classification, to Forecasting, to Optimisation, and Beyond, Kate Smith-Miles, Deakin University, Australia
10:20 PM - Concluding Remarks

Organization

Organizers

Christophe Giraud-Carrier, Brigham Young University, USA

Ricardo Vilalta, University of Texas at Houston, USA

Program Committee

Jonathan Baxter, Panscient Technologies, USA

Juan Botia, Universidad de Murcia, Spain

Philip Chan, Florida Institute of Technology, USA

Melanie Hilario, Univeristy of Geneva, Switzerland

Carlos Soares, LIACC, University of Porto, Portugal