CLOSE
BuzzfeedVideo on Facebook
BuzzfeedVideo on Facebook

An Algorithm Can Tell How Forgettable Your Selfies Are

BuzzfeedVideo on Facebook
BuzzfeedVideo on Facebook

According to a recent survey, the average millennial will take over 25,000 selfies in his/her lifetime. Science Alert reports that researchers at the Computer Science and Artificial Intelligence Laboratory (CSAIL) at the Massachusetts Institute of Technology (MIT) have developed a new algorithm that could help shutterbugs better distinguish between the forgettable and the memorable photos before posting them to social media accounts.

The algorithm is called "MemNet," and was actually designed to work for all photos, not just self-portraits. According to a CSAIL report [PDF] authored by graduate student Aditya Khosla and his MIT colleagues, MemNet uses a form of artificial intelligence called deep learning (also used in Google's Smart Reply automatic email system and in Apple's Siri) to develop ways to process data and find patterns on its own. "While deep-learning has propelled much progress in object recognition and scene understanding, predicting human memory has often been viewed as a higher-level cognitive process that computer scientists will never be able to tackle," principal research scientist Aude Oliva said. "Well we can, and we did!" 

To teach the algorithm what makes photos memorable, the researchers used the La Mem (large-scale image memorability) database of over 60,000 images that had been previously given "memorability scores" based on how well humans remembered them in trial experiments conducted online. After MemNet was able to find patterns for itself, it was tested against human subjects. "It performed 30 percent better than existing algorithms and was within a few percentage points of the average human performance," the CSAIL researchers said of the algorithm, which also creates a heat map of each image to highlight the most memorable section.

Examples from the La Mem gallery with high memscores. // La Mem

The researchers hope that the technology will help reveal more about how and what people remember. "This sort of research gives us a better understanding of the visual information that people pay attention to," UC Berkley Associate Professor Alexei Efros said. "For marketers, movie-makers and other content creators, being able to model your mental state as you look at something is an exciting new direction to explore."

To see how memorable your photos are, try the LaMem demo site created by the team at MIT.

[h/t: Science Alert]

nextArticle.image_alt|e
NASA / SwRI / MSSS / Gerald Eichstädt / Seán Doran // CC NC SA
arrow
Space
Mind-Bending New Images of Jupiter From Juno's Latest Flyby
NASA / SwRI / MSSS / Gerald Eichstädt / Seán Doran // CC NC SA

NASA’s Juno spacecraft left Earth in August 2011, and has been orbiting Jupiter since 2016, completing its eighth close flyby in late October. While flying beneath the dense cloud cover that obscures the solar system’s largest planet, it captured some incredible close-up views of the gas giant, as Newsweek reports.

With the JunoCam community, the public can alert NASA to points of interest and help direct the Juno mission. Citizen scientists have processed the raw, black-and-white images Juno beams back to Earth to highlight particular atmospheric features, collage multiple images, and enhance colors, releasing the edited color images before the space agency has a chance to. A whole new batch just emerged from the latest flyby, and they're well worth a look. Take a peek at a few below, and see more at the JunoCam website.

A swirl appears on Jupiter's surface.
NASA/SwRI/MSSS/Shawn Handran // Public Domain

A partial view of Jupiter
NASA/SwRI/MSSS/Shawn Handran // Public Domain

A close-up view of Jupiter's surface
NASA / SwRI / MSSS / Gerald Eichstädt / Seán Doran // CC NC SA

A view of Jupiter's surface
NASA / SwRI / MSSS / Gerald Eichstädt / Seán Doran // CC NC SA

[h/t Newsweek]

arrow
Stones, Bones, and Wrecks
Satellite Images Show Mysterious Nan Madol Ruins From a Brand-New Perspective

The ancient complex of Nan Madol on the island of Pohnpei in Micronesia has fascinated visitors for centuries. Now, thanks to satellite technology, researchers have captured the ruins from a perspective that's rarely seen.

As Yahoo 7 reports, the new aerial footage debuted on an episode of the Science Channel series What on Earth? In the recent installment, experts discussed Nan Madol, a chain of intricate, human-made islands that is sometimes called the "Venice of the Pacific" and is a UNESCO World Heritage Site. The name Nan Madol means "spaces between," a reference to the network of canals connecting the ruins.

The 100-odd blocky stone structures were built atop coral reefs in a lagoon off a remote island in the western Pacific Ocean. The walls of the artificial islands can reach up to 25 feet tall and are 17 feet thick in some parts. In total, the rocks that make up the site weigh nearly 827,000 tons. Archaeologists believe that portions of the city have been there for more than 1000 years, and that the site once served as the ceremonial, political, and residential hub for the native Saudeleur people. Little is known about how its builders were able to move such massive amounts of stone without levers, pulleys, or metal. 

Today, the Micronesian island of Pohnpei is home to 36,000 people, and even among locals, the landmark is notorious. Legends of spirits haunting the area have earned it the nickname "Ghost City." The ruins give off such an eerie vibe that H.P. Lovecraft used them as inspiration for the home of Cthulhu in a short story.

[h/t Yahoo 7]

SECTIONS

arrow
LIVE SMARTER
More from mental floss studios