Deep Learning Hyperparameter Optimization with Competing Objectives

Features, Deep Learning

Nadeem Mohammad, posted Aug 03 2017

In this post we’ll show how to use SigOpt’s Bayesian optimization platform to jointly optimize competing objectives in deep learning pipelines on NVIDIA GPUs more than ten times faster than traditional approaches like random search.

Read more

App Uses Deep Learning to Automatically Retouch Photos Before You Take Them

Research, Computational Photography, cuDNN, GeForce, Higher Education/Academia, Image Recognition, Machine Learning & Artificial Intelligence, Media & Entertainment

Nadeem Mohammad, posted Aug 02 2017

At this week’s SIGGRAPH conference, researchers from MIT and Google presented a new deep learning system that automatically retouches your photos like a professional photographer in real-time, before you even take them.

Read more

Coming Right Up! High Schoolers Build Indoor Delivery Robot with NVIDIA Jetson TX2

Research, Autonomous, DIGITS, Jetson, Machine Learning & Artificial Intelligence, Robotics, TensorRT

Nadeem Mohammad, posted Aug 02 2017

By Grace Lam, Mokshith Voodarla, Nicholas Liu How long does it take to program an office delivery robot? Apparently, less than seven weeks.

Read more

DesignWorks SIGGRAPH 2017 Announcements

News

Nadeem Mohammad, posted Aug 01 2017

Get the latest SDK and tools designed for developers creating professional graphics, advanced rendering, video processing, material design, and 3D printing.

Read more

Professional-Quality 3D Asset Library for Research Launched by NVIDIA, Amazon Lumberyard, and SpeedTree

News, Computer Graphics & Visualization, Games, Virtual Reality

Nadeem Mohammad, posted Aug 01 2017

By Aaron Lefohn, Director of NVIDIA Research Falcor Rendering R&D Framework Updated for DirectX 12 and Vulkan This morning at SIGGRAPH 2017, Amazon Lumberyard, SpeedTree, and NVIDIA announced ORCA (Open Research Content Archive) a free, open library

Read more