AI, trained on the basis of decades of culinary experiments, creates new dishes

Artificial intelligence (its weak form) penetrates science, art, military, games and many other areas. Now this technology is beginning to be applied in such an unexpected industry as cooking. The pioneer was IBM, which took advantage of Watson’s capabilities to create new recipes and improve existing ones.



Experts who work on the project, believe that if the test phase of the experiment goes well, then the AI ​​will have a significant impact on what we eat every day. The ideal is still very far away, but there is already some success.



IBM has worked with McCormick & Company, specifically its food experts, to explore the culinary field for several years in a row. The combined team taught AI how to create dishes, and next year Watson recipes will be available on the shelves. If this experiment is successful, then experts from McCormick & Company will work with AI technologies from 2021 onwards.

')

Representatives of the project say that with the help of Watson they want to create the best recipes in the world. Of course, all this also has a commercial background - McCormick & Company will deliver the results of successful experiments to the market. Watson will develop not only dishes, but also seasonings for them, as well as various mixtures.

Slow and not very confident

A representative of McCormick & Company said that it takes weeks and months to develop and bring a new food product to the market.



When a company creates a new product, dozens or even hundreds of experts begin to work on it - chemists, technologists, and culinary specialists. They develop individual components that later become part of the whole. If necessary, the components of the product are replaced or removed altogether until the final version approaches the ideal.



IBM's algorithms work much the same way - the system conducts experiments and selects the best result. But Watson remembers a lot more different formulas than one person or even a group of experts can remember. The AI ​​can experiment by mixing and sharing ingredients, getting the most unexpected combinations.



Developers believe that Watson can reduce the number of iterations required in the process of food product production and, in general, significantly reduce the time required for development.



AI works with a database that contains a huge number of different recipes, culinary experiments, descriptions of spices, etc.

And something else

The strength of the AI ​​is that it does not have a common opinion about what combinations of products should be in order to produce certain dishes. The main task of the system is to create what can be called delicious.



Watson is trained on McCormick & Company research data accumulated over the decades of the company's work. In addition, the algorithm receives information about the results of marketing research on the preferences of people regarding products, depending on such factors as culture, location, mood.



Experts believe that all this is required to take into account. Next year, as mentioned above, products, seasonings, sauces, created according to Watson's recipes, will go on sale. Many of them will be simply updated, without major changes, in order to improve the taste.



In the future, according to the developers, AI will completely change the world of cooking. Perhaps the AI ​​will pick up various new components, and the person will collect from this recipe cooking. Or the AI ​​will advise you to use sliced ​​garlic cloves for cooking a specific dish instead of garlic powder - and so it will be really tasty, and the sizes of the sliced ​​elements will be set by the system.



It may well be that in 20-30 years, people will not understand the previous generations who cooked food without the help of AI.