Over a decade ago, an artificially intelligent IBM computer by the name of Watson made history by defeating the reigning world chess champion. Since then, Artificial Intelligence (AI) has been a buzzword in the tech world, and has only gotten more sophisticated over time. We now have self-driving cars, intelligent traffic signals, and AI chefs – yes, you read that right.
Chef IBM Watson is a machine-chef that allows humans to cook unique, delicious food by proposing new recipes. What makes Chef Watson great is its ability to process huge amounts of food-related data to create new and tasty combinations of different ingredients. The people at Bon Appétit magazine have been using Chef Watson to support their cooks in creating tasty new food items.
The idea behind Chef Watson is that while humans are blessed with intuition, they normally find it difficult to think through large numbers different of food combinations. In other words, it is a daunting task for humans to work on massive amounts of data. That’s where Chef Watson comes in. Yes, a computer does not possess intuition (yet?), but it can work on huge amounts of data, try millions of different combinations, extract useful information out of the data, and retain the data on the best outcomes. Keeping this in mind, the researchers at IBM put their famous Watson to the test. They decided to combine recipe data from around the world, and then have Watson to come up with new combinations of ingredients.
Note that Chef Watson does not operate autonomously. It requires human input and feedback on its proposals. For example, when it proposed combining chocolate with blueberries, it needed to know from humans whether that particular combination tasted good or not so it could retain or discard the combination, and not propose it in the future. The project is a machine-human collaboration to enhance each other’s creativity.
Chef Watson built its knowledge by reading thousands of food recipes and studying their ingredients. From these recipes, it learned which ingredients are commonly used together, how they are used in different dishes, and how they are prepared. Combining this knowledge allows Chef Watson to come up with new combinations that it “thinks” might taste good. It proposes these combinations to the human cooks and asks for their feedback. Surprisingly, it is able to propose weird, new combinations of ingredients that result in great, if sometimes weird food – as confirmed by the professional food tasters at Bon Appétit.
From the cook’s perspective, you can give Chef Watson a particular food item you want to eat, say a pineapple and tell it how you want it to be served – on a pizza? In a hamburger? Chef Watson dives into its database to look for creative combinations of pineapple with other food items. It then comes up with one or more complete recipes for the new dish. The human cooks get the final say on which recipes to try.
There are people who fear AI will replace human workers. This is a practical example of an alternate path. At least for now, human cooks are still the ones lighting the fires.
Mazhar Naqvi is a CS grad student with research interests in computer networks and security. He can be reached at firstname.lastname@example.org and you can follow him on linkedin athttps://www.linkedin.com/in/mazharnaqvi
Learn how Unified Inbox’s UnificationEngine™ platform enables communications with complex systems through IoT Messaging at http://unificationengine.com!