Algorithm Identify depression by studying Instagram Photos

sad

Researchers used a machine-learning algorithm fed with Instagram streams to spot the correlations between depression and images. Depressed individuals prefer bluer, darker images and also received fewer likes than healthy people. Currently the detection rate is at 70 percent, which is a higher rate than GPs are able to identify.

Deep neural networks and machine-learning are key players of artificial intelligence. They are simulating basic information processing of the brain and are more and more used in many products.

More information: www.technologyreview.com

A Brain Prosthetic To Improve Memory

CqJ23AmW8AA0N-s

A startup named Kernel came out of stealth mode yesterday and revealed its ambitious mission: to develop a ready-for-the-clinic brain prosthetic to help people with memory problems. The broad target market includes people with Alzheimer’s and other forms of dementia, as well as those who have suffered a stroke or traumatic brain injury.

read more: http://spectrum.ieee.org/

Internet Archive: play 10.000 Commodore Amiga games

wb

The Internet Archive released over 10.000 Amiga games, which are now playable with an HTML5 Amiga-Emulator within your browser. The emulator is still under development and many games don’t start, but there is also the option to download the disc image as a ADF file, which could be played within other, proofed and stable desktop emulators like WinUAE.

Update: Unfortunately, the program has been taken down for further development.

More information: https://archive.org/details/softwarelibrary_amiga

World’s first tattoo by industrial robot

Within the Autodesk Pier 9 Artists in Residence program, the french company Appropriate Audiences has shown  a robot, which is tattooing a shin. One of the bigger challenges is to handle the uneven surface of the human body. The result is looking very neat and is showing the very high precision of the machine.

Robots will support us in many, even unexpected, tasks and are one of the most expressive ways to bring machine intelligence to (our) live(s).

More information: www.appropriateaudiences.net

Drones can be controlled via thoughts

Researchers at the Arizona State University have found a way to control drones with your thoughts. Before the commands are going to be send wirelessly to the drones a scullcap is used to collect the “navigators” brain activities which are processed with a software.

Even if you need to be highly concentrated and a special software and besides the fact that this system currently work with a set of just four drones it shows impressively what the combination of human thoughts and software is able to come up with.

More Information: https://asunow.asu.edu