Revolutionizing Recipe Recommendations: AI Model Separates Flavor Profiles from Ingredient Pairings
A new AI research breakthrough has led to the development of a model that can distinguish between ingredients that are commonly paired in recipes and those that share similar flavor molecules, opening up new possibilities for recipe recommendations and culinary discoveries. This innovation has the potential to transform the way we interact with food and cooking, making it easier for users to find new recipes and flavors to enjoy.
With "Epicure," London-based startup Kaikaku.AI presents three AI models that are the first to clearly separate whether an ingredient fits a recipe or is chemically related. Trained on 4.14 million recipes in seven languages and the FlavorDB flavor database, each variant returns different recommendations. The purely chemistry-based model even classifies taste and nutritional values better than the recipe-based alternatives, despite never seeing that information directly. The article Ask AI what goes with chicken and the answer depends on whether it learned from recipes or molecules appeared first on The Decoder.