Could AI provide us with tastier food than human cooks?
Can AI predict what our tastes are and provide us with better food than human cooks?
As absurd as this notion may sound, it seems that a large number of people living in the Western world love processed food and fast foods more than fresh meals.
And guess what? AI is probably going to help the food industry manufacture food which is much tastier than what we've been eating.
We've seen intelligent cooking robots in science fiction for decades, and now they finally seem to be becoming a reality. However, what is really amazing is not the development of the advanced functions of kitchen robots (that has culminated with Moley's human-like robotic arms), but the capabilities that AI has to understand our tastes.
The first, relatively simple, application of AI in cooking is the one used by PlantJammer and Foodpairing, two apps that create custom recipes using whatever ingredients are available to prepare an improvised meal. The developers collected data on aromas and flavors for years, and then (quite literally) fed it to the app's neural network. Eventually, the algorithms were able to find patterns that work well together and are now able to suggest palatable recipes to the user. While the first one is mostly used by common people to prepare a quick meal with leftovers, the latter is used by professionals to match different ingredients and create new recipes. Other AI-based kitchen assistants such as Chefling instead, simply suggest a recipe based on the ingredients available.
The most ambitious project, however, seems to be Gastrograph, an AI platform that could map taste preferences with allegedly amazing precision. Thanks to this technology, processed food could be made to match specific, individual tastes rather than just appeal to the masses. The data-collecting app is currently used by tasters who are prompted to describe their sensory experience through a wheel that describes 24 different tastes (such as "bitter," "meaty" or "exotic") with five levels of intensity. The Gastrograph also gathers additional data which may influence the user's tastes, such as socioeconomic status, demographics and past experiences with similar products.
Eventually, we can imagine that many other similar apps are going to be created to ultimately allow the food industry to know what each one of us really loves to eat. In the wake of these AI-driven technologies, the future is a world where we won't be eating Oreos with a taste that has been standardized to be always identical anymore. Instead, each one of us will be able to consume his or her custom-made beers, cookies, pizzas and chicken fries, each with a taste which perfectly matches individual preferences.
Have a question? Ask us here.
Written by Claudio Buttice
Dr. Claudio Butticè, Pharm.D., is a former clinical and hospital pharmacist who worked for several public hospitals in Italy, as well as for the humanitarian NGO Emergency.
He is now an accomplished book author who has written on topics such as medicine, technology, world poverty, and science. A freelance journalist as well, many of his articles have been published in magazines such as Cracked, The Elephant, Digital Journal, and Business Insider.
Dr. Butticè also published pharmacology and psychology papers on several clinical journals, and works as a medical consultant and advisor for many companies across the globe.Full Bio