Artificial intelligence keeps getting more intelligent.
Two years ago, the Google Brain team began employing machine learning techniques to teach a computer how to interpret and caption images. Sure, it won’t win any humor contests for being punny or particularly clever, but if you’re looking for a literal translation of what you’re looking at, Google’s AI system has you covered.
On Thursday, the internet giant announced that it had made “the latest version of our image captioning system available as an open source model in TensorFlow.” The most recent iteration of its AI “contains significant improvements to the computer vision component of the captioning system, is much faster to train, and produces more detailed and accurate descriptions compared to the original system,” Google said.
Called “Show and Tell,” the algorithm can recognize objects in imagery with an impressive 93.9 percent accuracy rate. That’s quite the improvement from just two years ago, when the AI was still scoring in the B-range, identifying images correctly just 89.6 percent of the time. So what’s changed? In essence, Google’s tool now tries to describe objects rather than simply classifying them.
“For example, an image classification model will tell you that a dog, grass and a Frisbee are in the image,” Google noted, “But a natural description should also tell you the color of the grass and how the dog relates to the Frisbee.”
While you may not need Google to tell you what you’re looking at on a daily basis, these machine learning capabilities could be used to help those with visual impairments, and further the work of other AI researchers. “We hope that sharing this model in TensorFlow will help push forward image captioning research and applications, and will also allow interested people to learn and have fun,” Google said.
For a full description of Google’s latest algorithm, check out “Show and Tell: Lessons learned from the 2015 MSCOCO Image Captioning Challenge,” published in IEEE Transactions on Pattern Analysis and Machine Intelligence.
A virtual private network (VPN) encrypts your internet traffic and routes it through a server run by the VPN provider. Websites see the VPN server’s IP address instead of yours, and you can get around geo-blocks, censorship, and ISP throttling. The best VPN services are paid, but there are still a handful of free options that do the job well.
Most free VPNs come with a hidden cost, because running servers isn’t cheap and a company that doesn’t charge you has to make its money somewhere else. Many do so by logging your browsing activity and selling it to advertisers, while others flood you with ads and track you across apps.
A stocked computer cache may be convenient for logging into and out of go-to sites in seconds flat, but a major buildup of these tracking codes could significantly impact your PC’s performance. If you’ve noticed that your PC has been running rather slow of late, or you’re using a new browser and don’t know how to clear its cache, we’ve got you covered with the following guide.
If you’re looking to clean up your Gmail inbox, but you don’t want to delete anything permanently, then choosing the archive option is your best bet. Whenever you archive an email, it is removed from your inbox folder while still remaining accessible. Here’s how to access any emails you have archived previously, as well as how to move such messages back to your regular inbox for fast access.