Independent Study On Support Vector Machines

SP. Augmented Reality. Psycho-Pass (2012)

Vacuum Tube - The Upgrade

—-

Graphic - Thomas A. Gieseke

Sony has opened pre-orders for its $840 SmartEyeglasses — complete with a bulky frame that makes Google Glass look positively unobtrusive.

Japan just sent the Int-Ball, a photo and video drone, to the International Space Station. Its mission is to document the astronauts. Previously, astronauts spent 10% of their time doing photo and video documentation. Int-Ball’s footage can be seen in real time.

follow @the-future-now

Artificial Intelligence Uses Less Than Two Minutes of Videogame Footage to Recreate Game Engine

This story is already doing the rounds but is still very interesting - Machine Learning research from Georgia Tech manages to clone game design from a video recording.

The top GIF is the reconstructed clone, the bottom gif is from the video recording:

Georgia Institute of Technology researchers have developed a new approach using an artificial intelligence to learn a complete game engine, the basic software of a game that governs everything from character movement to rendering graphics.

Their AI system watches less than two minutes of gameplay video and then builds its own model of how the game operates by studying the frames and making predictions of future events, such as what path a character will choose or how enemies might react.

To get their AI agent to create an accurate predictive model that could account for all the physics of a 2D platform-style game, the team trained the AI on a single “speedrunner” video, where a player heads straight for the goal. This made “the training problem for the AI as difficult as possible.”

Their current work uses Super Mario Bros. and they’ve started replicating the experiments with Mega Man and Sonic the Hedgehog as well. The same team first used AI and Mario Bros. gameplay video to create unique game level designs.

More Here

Adversarial Examples that Fool Detectors

Computer Vision research from Jiajun Lu, Hussein Sibai and Evan Fabry examines blocking neural network object detection using what appears to look like DeepDream-esque camouflage:

An adversarial example is an example that has been adjusted to produce a wrong label when presented to a system at test time. To date, adversarial example constructions have been demonstrated for classifiers, but not for detectors. If adversarial examples that could fool a detector exist, they could be used to (for example) maliciously create security hazards on roads populated with smart vehicles. In this paper, we demonstrate a construction that successfully fools two standard detectors, Faster RCNN and YOLO. The existence of such examples is surprising, as attacking a classifier is very different from attacking a detector, and that the structure of detectors - which must search for their own bounding box, and which cannot estimate that box very accurately - makes it quite likely that adversarial patterns are strongly disrupted. We show that our construction produces adversarial examples that generalize well across sequences digitally, even though large perturbations are needed. We also show that our construction yields physical objects that are adversarial. 

The paper can be found here

Inside the Blockchain Factory: How IBM's Distributed Ledger Work Went Global

IBM is building its blockchain work over a growing number of locations and employees, and Marie Wieck ties it all together. from CoinDesk http://ift.tt/2xbXrkC Donate Bitcoins 191LaSo6DsQFFMr9NQjyHBeYKLogfEYkBa

Abstract Poster Inspired by Ghost in the Shell

the last evening was a cool sightseeing tour, absolutly HOT #love #instagood #photooftheday #beautiful #fashion #happy #tbt #cute #followme #like4like #selfie #summer #fun #smile #style #amazing #sun #bestoftheday #pretty #cool #funny #ootd #potd #holiday #lifestyle #일상 #sweet #happiness #awesome #travel

Timelapse of Star Trails over Sparks Lake, Oregon