Neural Network

  • It's a novel idea, using light diffracted through numerous plates instead of electrons. And to some, it might seem a little like replacing a computer with an abacus, but researchers at UCLA have high hopes for their quirky, shiny, speed-of-light artificial neural network.
  • ​Robots that pick up and move objects (such as on assembly lines) may be useful, but they're typically only programmed to grasp specific types of objects that are placed in a specific orientation. Now, however, scientists have devised a method of allowing them to be more versatile.
  • Science
    ​While there are already portable keyboards that can be rolled up, we know how it is … sometimes you just want to crumple the thing up and jam it in your pocket. Well, new technology developed by South Korean scientists will allow you to do just that – plus the keyboards should be cheap, too.
  • Researchers from Nvidia have revealed an impressive new system that uses a deep-learning neural network to effectively create smooth high-quality slow motion videos from footage shot at a regular, low frame rate.
  • Don't like the idea of a stranger finding out who you are, based on a photo? Thanks to the facial recognition systems used by social media sites, it's becoming increasingly possible. Scientists decided to do something about it, by turning a couple of AI systems against one another.
  • If robots are ever going to earn their keep, they’ll need to learn on the job. AI researchers from Nvidia have now demonstrated a system that lets robots do just that, learning how to perform a specific task by watching someone do it just once.
  • Science
    Researchers are using GoPro cameras to train AI neural networks to behave and plan like dogs. By strapping a GoPro camera to an Alaskan Malamute's head, the team recorded 380 dog's-eye-view video clips which were then shown to the neural net to teach it how dogs are likely to behave.
  • Science
    ​When it comes to making city maps based on aerial photos, manually tracing all the roads can be quite the hassle. As a result, we're now seeing computer programs that do so automatically. Scientists at MIT have developed a program of their own, that is promised to be even better at the job.
  • Google's Magenta project has unveiled a hardware interface for an algorithm-based synthesizer that uses a deep neural network to generate completely new sounds. Musicians drag a finger around the NSynth Super's touchscreen to explore the unique sounds offered up by the machine learning algorithm.​
  • Science
    The human brain is a beast of a computer, but before we can emulate that we’ll need to start with something simpler. C. elegans is a worm whose basic brain of only 302 neurons has been digitized. Now researchers have taught this virtual worm a new trick, without writing a single line of code.
  • The brain is a far better computer than anything humans have ever built, so it’s not surprising that scientists are reverse-engineering it. Neuromorphic computers are built with networks of artificial neurons, and now a team has developed a more lifelike synapse to better connect those neurons.
  • It turns out that combining a CPU and a GPU into one package isn't the most unconventional processor Intel had up its sleeve for CES 2018. It has revealed a new quantum computer test chip containing 49 quantum bits (qubits), as well as a "neuromorphic" chip based on the function of the human brain.