Technology that makes Youtube the best video hosting service.

The most popular video hosting daily checksmillions of videos on the presence of banned or copyrighted materials, passing along the most interesting videos in recommended ones. Artificial intelligence, which is used in almost all sections of Youtube, helps to do this quickly and efficiently.

Search forbidden videos

In the first quarter of 2019, YouTube automatically deleted 8.3 million videos.  Algorithms worknot perfect, sometimes completely "clean" materials are removed, but most of the time the AI system justifiesthemselves.Scenes of violence, demonstration of dangerous actions, drugs - all this is successfully detected at the loading stage.

Before applying machine learning, malwarevideos were deleted using user complaints. According to statistics, only 8% of harmful material was seized before the 10th viewing. After the introduction of AI in the protection of Youtube, 50% of the prohibited content does not even reach 10 views.

Users are unhappy ifoffensive videos still gain hundreds of thousands of views, falling into the recommended ones. Brand companies often order ads on Youtube and don’t want them to appear in banned videos that offend the advertiser’s reputation.

External pressures are forcing Youtube developers to work hard to improve artificial intelligence to find prohibited content.For this purpose, machine learning is used to organize the work of the "bad video classifier" on the home page and in the "Next" section.With the help of big data, viewers' comments are analyzed, which helps to identify inappropriate content or "clickbait" – a video with a loud title, the content of which does not correspondName.

Next 

The "Next" section includes videos that are similar in content to the video you are watching.When Autoplay is turned on, it displays the first movie in the list that is in the Next section.This list is formed in two stages: the first one analyzes the user's browsing history.In the second stage, an independent ranking system is created that assigns a score to each video.

It is also necessary to take into account that thousands of videos are uploaded to Youtube every minute, which canWithout real-time processing with the help of artificial intelligence and big data technology, YouTube would simply not be able to cope with the search results, and instead of the long-awaited new issue of Amkal, a 7-year-old boy would have another music video or other video that was not interesting to him in autoplay.

Youtube as a training ground

Huge data stream is perfecttraining ground for AI. It turned out that the challenges spread on YouTube can be not only interesting, but also useful for studying augmented reality. As a result of processing more than 2000 videos with the popular mannequin-challenge in 2016, programmers got a good base for studying the depth of field of the video to improve VR technologies, the ultimate goal of which is the effect of full presence.

Terrorist Streamers

The terrible trend of streaming terrorist attacks began a few years ago and continues now.The shooter in Halle and the terrorist attack in New Zealand are not the first such cases.

The U.S. has already demanded that all streaming platforms develop  software that can identify dangerous individuals on live streams before they cause damagedamage to civilians. YouTube and Facebook are already working with the help of AIon the removal of terrorist content in cooperation with the Department of Justice and law enforcement.