MIT and QCRI's neural network knows how to make pizza

Photo of yummy pizza

MIT'due south Informatics and Artificial Intelligence Laboratory (CSAIL) and the Qatar Computing Enquiry Constitute (QCRI) have built a neural network that's capable of creating images of pizza before and after someone cooks information technology, co-ordinate toTheNextWeb.

The neural network is able to take an image of a pizza and figure out what the ingredients were and the correct way to layer the ingredients earlier sticking it in the oven. The bogus intelligence is able to understand what a pizza should expect like, from start to stop.

With it beingness able to do this, you can enquire the neural network to brand a Hawaiian pizza and ask information technology to remove pineapples, and it should exist able to generate an image of what that should look like. It'southward able to exercise this due to CSAIL and QCRI developing the AI with a modular approach.

CSAIL and QCRI's neural network has a pre-cooking phase and can make the pizza wait appealing and making sure information technology tastes skillful every bit well, or at least in theory.

The researchers go on by saying:

Though we have evaluated our model simply in the context of pizza, we believe that a similar approach is promising for other types of foods that are naturally layered, such as burgers, sandwiches, and salads. Beyond food, it volition exist interesting to see how our model performs on domains such as digital fashion shopping administration, where a key functioning is the virtual combination of unlike layers of clothes.

Significant that the neural network could help users become dressed and brand a perfect sandwich.

It'll even so be a while earlier a robot tin build your pizza, unfortunately.

Source: TheNextWeb