AI will Help You Make Beer with Whatever Ingredients You Have!
The beer business will see a new revolution with this unique AI model.
Another Feather is soon to be added to the hat of AI’s never-ending capabilities. AI that mimics aspects of the behavior of flies seeking food can now be used to design new beer recipes. It can also accurately recreate an existing brew using alternative ingredients when supplies are unstable.
AI could also help brewers predict the attributes of a beer from a new recipe before it is actually produced. Its ultimate color, alcohol content, and bitterness, for example, could be gleaned from the choice of ingredients. Machine learning techniques are being investigated to help create novel beers. The researchers aimed to model the relationship between a beer recipe and various attributes. In one trial, they focused on beer type, to see if their system could classify a recipe as ale, lager, or wheat beer. In another task, their model aimed to categorize beers into one of 81 specific types, such as American IPA (India Pale Ale) or Dry Stout. In a third experiment, the model would try to predict ranges for 10 different attributes, such as bitterness units or color.
The team used two different deep learning models to compare the predictions generated. One of them is called a Deep Neural Network (DNN), which is simple and widely used and is able to learn the features of individual ingredients in a recipe. The second model, however, called Long Short-Term Memory (LSTM), is more complex, as it learns from sequences of ingredients. A collection of over 200,000 beer recipes shared by homebrewers on a publicly available website was used as data for the experiments. The two deep learning models were trained with 70% of the recipes, while the rest was retained for testing purposes afterward. In the complex classification task with 81 beer types, the model demonstrated the accuracy of about 34%, which is quite low. However, the team was able to use visualization techniques to confirm that the model was learning meaningful structures in the recipes.
Deep learning models could be useful tools for breweries, where it often takes three months or more to develop a new beer. In addition to predicting the attributes of a beer, such models could be used in reverse to generate recipes based on desired attributes.
Another group of researchers investigated whether deep learning could generate new beer recipes. Having previously used AI to adapt cooking recipes, these researchers decided to see if a similar approach could be applied to create new beers. To their knowledge, it hadn’t been done before starting from a partial or empty list of ingredients. The team collected over 150,000 beer recipes from both professional and hobby brewers around the world, which were featured on the same publicly available website. The set of recipes, which contained information such as ingredient amounts and processing steps, was then refined to a training and testing set of over 65,000 recipes.
On average, the recipes generated were more novel than those in the test set. The researchers also had a professional brewer evaluate the feasibility of producing the recipes, based on various factors such as cost of ingredients and technical aspects. Just under a third of the AI-generated recipes were considered to be fit for production. The ultimate test, however, was to brew a beer whose recipe was created with deep learning. A local microbrewery used the team’s recipe generator to create a recipe for an India Pale Ale (IPA) beer. They then produced the beer, aptly called Deeper, which had a grapefruit-like flavor.