Metaheuristics "In the Large"

no code implementations • 19 Nov 2020 • Jerry Swan, Steven Adriaensen, Alexander E. I. Brownlee, Kevin Hammond, Colin G. Johnson, Ahmed Kheiri, Faustyna Krawiec, J. J. Merelo, Leandro L. Minku, Ender Özcan, Gisele L. Pappa, Pablo García-Sánchez, Kenneth Sörensen, Stefan Voß, Markus Wagner, David R. White

We describe our vision and report on progress, showing how the adoption of common protocols for all metaheuristics can help liberate the potential of the field, easing the exploration of the design space of metaheuristics.

L2AE-D: Learning to Aggregate Embeddings for Few-shot Learning with Meta-level Dropout

no code implementations • 8 Apr 2019 • Heda Song, Mercedes Torres Torres, Ender Özcan, Isaac Triguero

(b) We also introduce a simple meta-level dropout technique that reduces meta-level overfitting in several few-shot learning approaches.

Few-Shot Learning

Combining Monte-Carlo and Hyper-heuristic methods for the Multi-mode Resource-constrained Multi-project Scheduling Problem

no code implementations • 13 Nov 2015 • Shahriar Asta, Daniel Karapetyan, Ahmed Kheiri, Ender Özcan, Andrew J. Parkes

Multi-mode resource and precedence-constrained project scheduling is a well-known challenging real-world optimisation problem.

Scheduling