Will the food of the future be based on AI-created recipes?
Anyone who has spent even the slightest amount of time on social media has witnessed the proliferation of pictures of food. Along with these shots of healthy salads, juicy steaks, and indulgent desserts come descriptions and reviews.
All the collected data is ideal for developing AI and machine learning, which can then use the information to create new recipes. Additionally, artificial intelligence can be used to create food that optimizes nutritional value and flavor by using the knowledge gained from millions of pictures and descriptions.
Reverse-Engineering Food
MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL), working with the Qatar Computing Research Institute and Universitat Politecnica de Catalunya, developed Pic2Recipe, an artificial intelligence system that discovers recipes from pictures of food.
The artificial neural network (ANN) read more than a million recipes and found patterns between ingredients and the pictures. Pic2Recipe was largely successful but needs some further refinement when evaluating pictures of food that contains many different ingredients, such as lasagna.
As the technology is refined, neural networks such as Pic2Recipe can help consumers know what is in their food and the exact amount of each ingredient. Such an advancement could be of great significance to those with allergies or those who are trying to adhere to very specific diets.
AI Cooking Assistants
Similar technology is currently available in the palm of your hand. Mobile apps such as PlantJammer and Chefling help create recipes using ingredients that are already in your house. PlantJammer generates vegetarian recipes based on users’ preferences by using existing aroma profiles to combine ingredients in different ways. The app also allows users to find ingredients to add based on desired flavor and texture profiles.
Chefling pairs with smart appliances in the kitchen and smart assistants, including Alexa and Siri, to provide recipes that are ready to be cooked or a list of missing ingredients for specific recipes that need to be bought at the store. The app syncs with other family members to update shopping lists in real time and uses machine vision to scan receipts to add purchases to its inventory.
Additionally, AI meal planners such as Noom, Habit, and Beyonce’s 22 Days use machine learning to develop personalized weight loss and nutrition solutions for users. By evaluating exercise routines and eating habits — and in the case of Habit, cholesterol and triglyceride levels — AI-powered meal planners can help tailor individualized lifestyle changes for the better.
Creating AI Food
Earlier this year, spice giant McCormick partnered with IBM Research for their assistance in using artificial intelligence to create new flavors. McCormick, which was founded 130 years ago, has collected a staggering amount of information on past recipes and flavors and their reception by consumers. IBM’s AI can sift through that data, recognize patterns, and create new flavor profiles according to desired outcomes.
In a company blog post, IBM further explained the benefits of the partnership, stating, “Our system includes algorithms that can learn and predict: Possible alternative raw material complements and substitutes for a formula; appropriate ratios of raw materials based on usage patterns; human response; (and) novelty of system-generated flavor formulas as measured by a derived distance function (the larger the distance between a flavor formula and its nearest neighbors, the more novel the flavor formula is predicted to be).”
Gastrograph AI is another company harnessing the power of machine learning to make AI food and beverages. The company offers an AI platform that simulates human sensory perception in order to predict responses to flavor profiles. Gastrograph AI states its goal as helping “producers to model, understand, and optimize the flavor, aroma, and texture of their product for target consumer demographics and cohorts.”
AI Alcoholic Beverages
Having already begun making its way to the dinner table, AI is also on its way to bars and liquor cabinets. Data consultancy company 10X recently developed IntelligentX, which is billed as “the world’s first beer brewed by artificial intelligence.”
Originally developed to prove the value of data, the beer became so popular that it spun off into its own company. An algorithm compiles feedback submitted by customers through Facebook Messenger and sends suggestions to the brewer. IntelligentX offers a subscription service in the UK with plans to expand internationally.
In the US, Virginia-based Champion Brewing teamed with Skafos (formerly Metis Machine) to craft “the perfect IPA.” The logarithm included SRM (Standard Reference Method or the color of the beer), ABV (Alcohol by Volume), and IBU (Intrenational Bitterness Unit), as well as information of the best-selling beers nationally, and the worst-selling beers locally. The result was ML IPA, with a 6 SRM, 6 percent ABV, and 60 IBU.
On the liquor front, Swedish distillery Mackmyra has crafted “the world’s first AI-whisky.” The company used Microsoft Azure to feed AI recipes, customer preferences, and sales figures. Ultimately, the computer generated recipes that feature unique combinations never imagined by the company’s Master Blender Angela D’Orazio who then added the human touch in selecting the final recipe.
The Future of AI Food and Drinks
A future of AI food, made from recipes devised by ANNs, is not far off and could ultimately lead to healthier, tastier foods. While some may initially scoff at the idea of algorithms and neural networks without taste buds creating our recipes and influencing our diet, food and beverage trends can change rapidly.
It was not so long ago that vegetarianism and veganism were niche markets, but the rapid rise of Impossible Foods and Beyond Meat prove these diets have gone mainstream. AI food could be next.
Leave a Reply