An algorithm created to identify recipes for food just from a photograph has been demonstrated by researchers at the Massachusetts Institute of Technology (MIT).
The neural network was trained on a dataset of one million photos and one million recipes.
The trial model worked best on desserts and found smoothies and sushi more challenging, the researchers said.
The team has released an online trial although it is not a finished product.
When tested by the BBC, recipes that were generated based on a picture of spaghetti bolognese included “Italian tomato sauce” and “gunk on noodles”.
July 24, 2017
featured blogs
Apr 25, 2024
Structures in Allegro X layout editors let you create reusable building blocks for your PCBs, saving you time and ensuring consistency. What are Structures? Structures are pre-defined groups of design objects, such as vias, connecting lines (clines), and shapes. You can combi...
Apr 24, 2024
Learn about maskless electron beam lithography and see how Multibeam's industry-first e-beam semiconductor lithography system leverages Synopsys software.The post Synopsys and Multibeam Accelerate Innovation with First Production-Ready E-Beam Lithography System appeared fir...
Apr 18, 2024
Are you ready for a revolution in robotic technology (as opposed to a robotic revolution, of course)?...