Towards Feature-Free Automated Algorithm Selection for Single-Objective Continuous Black-Box Optimization

We propose a novel method for automated algorithm selection in the domain of single-objective continuous black-box optimization. In contrast to existing methods, we use convolutional neural networks as the selection apparatus which bases its decision on a so-called 'fitness map'. This fitn...

Celý popis

Podrobná bibliografia

Vydané v:	2021 IEEE Symposium Series on Computational Intelligence (SSCI) s. 1 - 8
Hlavní autori:	Prager, Raphael Patrick, Vinzent Seiler, Moritz, Trautmann, Heike, Kerschke, Pascal
Médium:	Konferenčný príspevok..
Jazyk:	English
Vydavateľské údaje:	IEEE 05.12.2021
Predmet:	Automated Algorithm Configuration Benchmark testing Black-Box Optimization CMA-ES Convolutional neural networks Deep Learning Feature-Free Gray-scale Performance gain Point cloud compression Reinforcement learning Two dimensional displays
On-line prístup:	Získať plný text
Tagy:	Pridať tag Žiadne tagy, Buďte prvý, kto otaguje tento záznam!