The DARPA researchers have come up with autonomous drones which can have huge impacts on search and rescue operations during natural calamities such as earthquakes, floods, tornadoes. For those of you who may not be very well aware of the topics of drones please see the video below. Drones or the commercially available quadcopters are the smallish flying electronic set of devices which can seem like tiny helicopter-like things and have huge applications. Their users range from hobbyists in the backyard to governmental agencies. These drones typically have four rotor-blades which propel them and are arranged in a diamond or rhombus shape. The drones fundamentally consist of a battery to power the drone, a set of blades/propellers which are controlled by motors and a flight system which acts as the brain which tells the drones what to do and how to fly. The challenge which the scientists at DARPA were posed was that suppose the drone neither has access to the
Researcher's at MIT's CSAIL design PixelPlayer a deep-learning based AI system to enable audio editing in music videos. Introduction Have you ever tried using Youtube or Dailymotion to try and learn how to play a part of your favorite song on a guitar or another musical instrument? A team of researchers at the Massachusetts Institute of Technology ’s CSAIL (Computer Science and Artificial Intelligence Laboratory) just made your life easier. The researchers at CSAIL have designed a system called PixelPlayer which enables a user, given a music video containing musical instruments playing sounds, to identify the pixels, or simply the region of the video being clicked , with the sound associated with it. Essentially what you can do is that if say in a music video a trumpet is being played in addition to another musical instrument, when you click on the trumpet the Artificial Intelligence -based system called PixelPlayer will only identify the sound of