Technology 3 min read

MIT Scientists Train an AI To Create the Perfect Pizza

Free-Photos / Pixabay

Free-Photos / Pixabay

Researchers at Massachusetts Institute of Technology have trained a new artificial intelligence on how to create the perfect pizza.

Creating the perfect pizza takes patience, practice, time, and most importantly, skill. With such a high requirement, it makes you wonder if machines can pull-off what took years for professional chefs to perfect.

The MIT researchers finally provided an answer to that question.

According to a paper in, MIT researchers taught an AI how to reverse engineer pizza. To be specific, they used machine learning to transform a pizza image into a step-by-step guide on how to create it.

Yes, it sounds a bit whimsical. However, this tech has the potential to disrupt the food sector completely.

Imagine an exciting new world where you could get a food’s recipe by merely taking a picture of it. That’s what this AI offers.

How does it work, you ask?

Using an AI Chef to Create the Perfect Pizza

MIT Scientists Trained AI To Create the Perfect Pizza
Image Credit: MIT

The MIT researchers started PizzaGan project as an experiment to teach machines how to make pizza. To do this, the machine must recognize every aspect of cooking – from adding or subtracting ingredients to preparing the dish itself.

So, the researchers fed about 5,500 images of pizzas – with up to 10 photos of labeled toppings – into the machine. Next, they added additional 9,213 images of real pizza from Instagram.

With this dataset, the AI was able to recognize various pizzas and the steps involved in its making. Not only could the machine determine the toppings on each pizza, but it could also understand the order in which they were placed.

As a result, the pizza AI could produce an image of what a pizza would look like with or without specific toppings. It could also create a before and after cooking picture of a pizza.

Analyzing Layered Foods

Although PizzaGAN only works with pizza at the moment, the researchers believe it could do much more.

With its ability to manipulate layers, not only could it work on other foods such as salad and burger, but it could also be useful in the fashion industry.

The researchers wrote in the paper:

“It will be interesting to see how our model performs on domains such as digital fashion shopping assistants, where a key operation is the virtual combination of different layers of clothes.”

The MIT team hopes to create a digital shopping assistant that could create a fancy outfit from various layers of clothing.

Read More: Researchers Use Electric Tongue To Accurately Evaluate Food Spiciness

First AI Web Content Optimization Platform Just for Writers

Found this article interesting?

Let Sumbo Bello know how much you appreciate this article by clicking the heart icon and by sharing this article on social media.

Profile Image

Sumbo Bello

Sumbo Bello is a creative writer who enjoys creating data-driven content for news sites. In his spare time, he plays basketball and listens to Coldplay.

Comments (0)
Most Recent most recent
share Scroll to top

Link Copied Successfully

Sign in

Sign in to access your personalized homepage, follow authors and topics you love, and clap for stories that matter to you.

Sign in with Google Sign in with Facebook

By using our site you agree to our privacy policy.