Gizmorama - December 23, 2015

Good Morning,

A computer algorithm has been designed to measure just how memorable an image is. How do you think a picture of you would rate after the "MemNet" algorithm takes a gander?

Learn about this and more interesting stories from the scientific community in today's issue.

Until Next Time,
Erin

P.S. Did you miss an issue? You can read every issue from the Gophercentral library of newsletters on our exhaustive archives page. Thousands of issues, all of your favorite publications in chronological order. You can read AND comment. Just click GopherArchives

***
*-- How boring is your face? Ask the 'MemNet' algorithm --*
BOSTON - Scientists at MIT's Computer Science and Artificial Intelligence Laboratory have designed a computer algorithm that measures how memorable an image is.

Feed it a photo from your Instagram feed and the "MemNet" algorithm will show you the portions of the image most likely to stick in the memories of viewers. A version of the algorithm is online for anyone to try.

Researchers recently detailed their technology in a new scientific paper.

MemNet is a deep-learning algorithm, meaning it is built to acquire and incorporate new information to improve its abilities without the manipulation or control of human programmers. Deep-learning technologies work by mimicking the neural pathways associated with human learning and repurposing them for various skill sets.

Ostensibly, MemNet will improve its ability to predict an image's indelibility simply doing its job and processing more information. Computer engineers designed MemNet and have now let it out into the world to be the best it can be.

MIT scientists first endowed MemNet with its skills by uploading thousands of images and associated data. The metadata included information about each image's popularity and emotional impact as determined by online viewers.

MemNet performs about as well as a human when asked to predict which photos are likely to be most memorable.

"Understanding memorability can help us make systems to capture the most important information, or, conversely, to store information that humans will most likely forget," lead study author Aditya Khosla, a grad student at CSAIL, told MIT News. "It's like having an instant focus group that tells you how likely it is that someone will remember a visual message."

Though MemNet is currently no better than humans at the task of measuring memorability, researchers expect it to get better over time. Its analysis is also able to pinpoint which portions of a picture are key to its memorability -- creating a heatmap that shows the memorable parts and boring parts of each image.

Eventually, the algorithm may be able to help marketers and movie makers edit their imagery to more effectively get inside the heads of their customers and viewers.

Or more benevolently, as MemNet learns, it can help others learn more efficiently, too.

"You might expect that people will acclimate and forget as many things as they did before, but our research suggests otherwise," Khosla said. "This means that we could potentially improve people's memory if we present them with memorable images."


*-- New research reveals secrets of spider web's signal thread --*
OXFORD, England - Web-building spiders don't often bask in the glory of their creation. They hang out off-screen, keeping tabs on their arrangement via a special strand of silk fibers, a signal thread.

Until now, researchers weren't exactly sure how this communicative thread worked. New research out of the University of Oxford has offered insights into how the sector web spider uses its solitary signaling thread.

The signal thread of the sector web spider -- sometimes called the missing sector orb weaver or the silver-sided sector spider -- serves two purposes, acting as a monitoring tool and as the arachnid's main route of escape.

"The spiders that employ signal threads seem to make the most of the added protection from a retreat, while still being able to detect the important web vibration signals from afar," researcher Beth Mortimer, a zoologist at Oxford, said in a press release.

Mortimer and her colleagues were surprised to find signaling threads measured in the field varied in thickness. Some were composed of as few as four silk fibers while others had as many as 16.

In documenting the spiders' use of their webs and signal threads, researchers realized each time a spider travels across its escape line it adds another fiber, making it stronger.

"The implications of the variable structure of the signal threads are carefully controlled by the spider," Mortimer said. "As more fibers are added to the signal thread, the spider carefully tensions each one to simultaneously increase the overall tension of the signal thread. This is important, as the vibrational properties of the signal thread remain constant across many different signal thread sizes."

The woven fibers are structured so that they act as a single thread, carrying vibrations efficiently.

"Overall, the signal thread structure and properties give freedom to the spider to move along the signal thread to and from the web as opportunities for prey capture arise," added Mortimer.

The findings, published in the journal Interface, could be used to inspire remote signalling technology or to improve devices that convert vibrations into electricity.

***
Missed an Issue? Visit the Gizmorama Archives