Artificial Intelligence, or AI as it’s known, is now a big part of our daily lives, often more than what we might expect, showing up everywhere from smartphone apps to our Netflix queues, voice-powered personal assistants like Siri and Alexa, Amazon shopping recommendations and even mundane things like your email spam filter! All use AI. While machines haven’t taken over – not yet at least, they are seeping their way into our lives.
When it comes to eating, technology is also becoming an increasing – if not always obvious – part of the dining experience at quick serve and fast casual restaurants. In many eateries we already encounter and interact with self-serve options, kiosks, voice assistant-enabled ordering, chatbots, delivery, and now it seems that AI is to play a bigger role in developing the foods we eat every day –perhaps even, the making of the perfect pizza.
What are we talking about? MIT researchers have taught a new artificial intelligence how to reverse engineer pizza — specifically, they’ve trained an AI to look at a photo of pizza and determine both the toppings on it and the order in which they were placed. The PizzaGAN (Generative Adversarial Network) project is described as an experiment in how to teach a machine to make a pizza by view a single image, dissect and identify each object, add and subtract ingredients, manipulate layers, and recreate a step-by-step guide to cook it. So, if you have a photo of a pizza with mushroom, pepperoni, and olives, PizzaGAN is potentially able to identify the three toppings and predict the order the toppings appear in the cooking process.
So, what’s the point of it all? One article featured on Gizmodo described the project as “research mostly just demonstrating an AI’s ability to differentiate between a confusing pile of ingredients“. In its current form that could be deemed as a pretty accurate summation but down the line the research could have wider implications. While PizzaGAN isn’t making real pizzas yet, the results of the program have shown that it doesn’t need much human supervision to put together a decent pie (at least on a digital screen) with 88 percent accuracy. In the long run, one could imagine a neural network being able to scan a photo and spit out a pretty accurate recipe based on ingredients, how thoroughly it’s cooked, and even barely visible spices – and not just pizza at that.
MIT are not the only ones looking at pairing AI with the food industry. IBM Research, in collaboration with McCormick & Company, a pioneer in flavor and food innovation, have also created a novel AI system to help product developers more efficiently and effectively create new flavor experiences and formals and also generate recipes that a human might not have considered. By combining the expertise of world food experts along with all the AI research and development, in the future AI might not only be responsible for speeding up the physical creation of our food but may actually also include AI-generated foods, flavors, and mixtures based on a deep knowledge of flavor profiles so complex that no human expert could match it.
While it’s unlikely that pizza bots will be popping up, cooking and serving your food anytime soon, one thing is for sure – as technology becomes more sophisticated, AI and automation in quick serve and fast casual restaurants will play an even greater part of the entire process than just automated ordering kiosks touching every aspect of the industry, from ordering and staffing to serving and food preparation itself.