Exploring the SpaceNet Dataset Using DIGITS

Features, Computer Vision, Deep Learning, DetectNet, DIGITS, Object Detection

Nadeem Mohammad, posted Aug 31 2016

DigitalGlobe, CosmiQ Works and NVIDIA recently announced the launch of the SpaceNet online satellite imagery repository. This public dataset of high-resolution satellite imagery contains a wealth of geospatial information relevant to many downstream use cases such as infrastructure mapping, land usage classification and human geography estimation. The SpaceNet release is unprecedented: it’s the first public

Read more

VR Funhouse Source and Mod Kit now available for Modders

GameWorks, VRWorks

David Coombes, posted Aug 31 2016

VR Funhouse is NVIDIA's first game. Built with Unreal Engine, it's a VR experience packed with technology from VRWorks and GameWorks. Developers and modders can now access the source, using the VR Funhouse Mod Kit, allowing them to create mods and games to share with the world via Steam Workshop.

Read more

High School Student Using Artificial Intelligence to Fight Breast Cancer

News, Research, CUDA, cuDNN, GeForce, Higher Education / Academia, Image Recognition, Machine Learning & Artificial Intelligence, Medical and Life Sciences

Nadeem Mohammad, posted Aug 30 2016

What started as a tenth-grade class project, the high school senior believes his technology can take on potentially deadly breast tumors and non-cancerous growths by using a mobile phone or tablet to aid in diagnosis and classification, reduce human error and save the expense of false-positive readings. Abu Qader, who’s in his final year at

Read more

What’s your Vulkan Memory Type?

Vulkan, GameWorks, GameWorks Expert Developer, DesignWorks

Mathias Schott, posted Aug 29 2016

Authors: Mathias Schott & Jeff Bolz

This blog post discusses recent improvements and additions to the memory management interface of our Vulkan implementation, based on collaborating with game developers porting their games to Vulkan.

Read more

Deep Learning to Unlock Mysteries of Parkinson’s Disease

Research, cuDNN, GeForce, Higher Education / Academia, Image Recognition, Machine Learning & Artificial Intelligence, Medical and Life Sciences, Virtual Reality

Nadeem Mohammad, posted Aug 26 2016

Researchers at The Australian National University are using deep learning and NVIDIA technologies to better understand the progression of Parkinson’s disease. Currently it is difficult to determine what type of Parkinson’s someone has or how quickly the condition will progress. The study will be conducted over the next five years at the Canberra Hospital in

Read more