Published: Ven, Mai 04, 2018
Médecine | By Giselle Gaudin

Facebook's artificial intelligence learns to see thanks to Instagram hashtags

Facebook's artificial intelligence learns to see thanks to Instagram hashtags

The post Facebook utilizes Instagram photos and hashtags to create a smarter A.I. appeared first on Digital Trends.

Facebook is leveraging billions of Instagram photos and thousands of user-added hashtags to improve the state of the art of image recognition.

From its early days, hashtags have been one of the most fundamental parts of content sharing on any social media.

A recent report shows that Facebook trained its image recognition machine by feeding it 3.5 billion photos from Instagram.

While companies and researchers around the world work to build the most advanced and powerful AI systems, Facebook has a special treasure trove that most don't: billions of tagged photos thanks to Instagram. So, it won't be using hashtags to figure out which of your Facebook friends is your #bff.

More news: Kane Wins Knox County Mayor Republican Primary

A "supervised learning process often yields the best performance results", the post reads, "but hand-labeled data sets are already nearing their functional limits in terms of size". While other image recognition benchmarks may rely on millions of photos that human beings have pored through and annotated personally, Facebook had to find methods to clean up what users had submitted that they could do at scale. Compared to the usual method of teaching AIs to categorize photos using visual clues, this method was much faster and less labor-intensive.

"The crux of this approach is using existing, public, user-supplied hashtags as labels instead of manually categorising each picture,"noted Mahajan and team".

Using this strategy, called "weakly supervised training", Facebook's AI achieved a record 85.4% accuracy rating on an industry-wide test of image recognition, beating out Google's previous record.

The "pre-training" research focused on developing systems for finding relevant hashtags; that meant discovering which hashtags were synonymous while also learning to prioritize more specific hashtags over the more general ones.

Like this: