Deep-learning Webinar Demonstrates Handwriting Recognition and Efforts to Teach Drone to Fly Down a Wooded Path

Deep-learning is a computational expensive but rewarding method to solve many complex pattern recognition problems. The recent NVIDIA webinar by Dan Claudiu Cireșan, Senior Researcher at the Dalle Molle Institute for Artificial Intelligence (IDSIA) in Switzerland highlighted some of the capabilities of deep-learning for image recognition problems such as handwriting recognition and on-going work to have a drone fly itself done a wilderness path. Check out the on-demand video of his talk below.

Click on image to learn more about Dan Cireșan

Deep-learning has experienced a recent resurgence of interest due – in part – to the teraflop per second of GPUs, which have the computational power to perform training on complex data sets. Check out our exascale capable deep-learning code on github that achieved 13 PF/s average sustained performance on the ORNL Titan supercomputer.

Click to view article

IBM is demonstrating the SyNAPSE chip, that has a similar number of neurons as the brain of a bee.

Click to view article