Smart Chef - Evolving Recipes
Proceedings of Evostar 2019 and Master Thesis - Carsten Felix Draschner supervised by Hajira Jabeen, Jens Lehmann
TL;DR ⏱️
- Evolutionary Algorithm for Culinary Arts
- Autonomous Recipe Evolution
- Master Thesis
- University of Bonn
The evolutionary algorithm for Smart Chef is fully automated and does not require human feedback. The tree representation of recipes is inspired by genetic programming and is enriched with semantic annotations extracted from known recipes. The fitness function identifies valid recipes and novelty. Recipe mutation exchanges ingredients by food category classification and recombination interchanges partial recipe instructions. Smart Chef has been tested on a population size of 128 and evolved for 100 generations, resulting in valid and novel recipes.