Facebook researchers teach AI about visual perception

The researchers explained that AI is capable of dozens of manipulations based on existing data. therefore

engineers from Facebook decided to add to the processlearning "common sense". With this option, machine learning doesn't need to upload 500 photos of a cat before the AI ​​can detect the animal. New research on social networking will avoid this learning step.

Scientists shared how they improved and scaled advanced computer vision algorithms. One of the interesting areas of Facebook development is "semi-supervisor training".

Facebook researchers have shown by example thatlearning can be challenging but very effective. The DINO system (DIstillation of knowledge with NO labels) is able to find objects of interest in a video without tagged data.

To do this, the system does not consider the video asa sequence of images to be analyzed in order, but as a complex, interconnected set of data. By paying attention to the middle and the end of the video, the AI ​​can get an idea of ​​things like "an object of such and such a shape moves from left to right." This information is used for further analysis. Scientists note that the system does not work mechanically, but develops a basic sense of visual meaning without a huge amount of training.

As a result, the system shows goodresults compared to traditionally trained systems. Researchers have shown that an AI trained on 500 photographs of dogs and 500 photographs of cats recognizes both, but cannot understand how they are similar. But Facebook's algorithm is able to distinguish them because of "common sense" and visual perception of pictures.

Read more

Elon Musk: the first tourists to Mars will die

The first accurate map of the world was created. What's wrong with everyone else?

A dead star has been discovered rotating on its axis in a second

Facebook Notice for EU! You need to login to view and post FB Comments!