Programming Tensor Cores in CUDA 9

Artificial Intelligence, CUDA, cuDNN, Machine Learning & Artificial Intelligence, Tesla

Nadeem Mohammad, posted Oct 17 2017

A defining feature of the new Volta GPU Architecture is its Tensor Cores, which give the Tesla V100 accelerator a peak throughput 12 times the 32-bit floating point throughput of the previous-generation Tesla P100.

Read more

Mixed-Precision Training of Deep Neural Networks

Artificial Intelligence, Machine Learning & Artificial Intelligence, Tesla

Nadeem Mohammad, posted Oct 12 2017

Deep Neural Networks (DNNs) have lead to breakthroughs in a number of areas, including image processing and understanding, language modeling, language translation, speech processing, game playing, and many others.

Read more

Training AI for Self-Driving Vehicles: The Challenge of Scale

Artificial Intelligence, Autonomous Vehicles, Automotive, Machine Learning & Artificial Intelligence, Tesla

Nadeem Mohammad, posted Oct 10 2017

Modern deep neural networks, such as those used in self-driving vehicles, require a mind boggling amount of computational power.

Read more

Style Transfer From Multiple Reference Images

Artificial Intelligence, CUDA, Higher Education/Academia, Image Recognition, Machine Learning & Artificial Intelligence, Media & Entertainment, Tesla

Nadeem Mohammad, posted Oct 04 2017

Researchers from Microsoft and Hong Kong University of Science and Technology developed a deep learning method that can transfer the style and color from multiple reference images onto another photograph.

Read more

AI Helps You Paint Like Van Gogh

Artificial Intelligence, Features, Image Recognition, Machine Learning & Artificial Intelligence, Media & Entertainment, Tesla

Nadeem Mohammad, posted Sep 27 2017

Product design and development firm Cambridge Consultants developed a deep learning-based system that turns human sketches into paintings that resemble Van Gogh, Cézanne and Picasso.

Read more

PGI 17.7 Delivers OpenACC and CUDA Fortran for Volta GPUs

Accelerated Computing, Features, Cluster/Supercomputing, CUDA, OpenACC, Tesla

Nadeem Mohammad, posted Sep 14 2017

PGI compilers & tools are used by scientists and engineers who develop applications for high-performance computing (HPC) systems.

Read more

AI Drones Help Inspect Industrial Equipment

Artificial Intelligence, Features, Robotics, Smart Cities, Architecture/Engineering/Construction, Energy/Oil & Gas, Image Recognition, Machine Learning & Artificial Intelligence, Manufacturing, Tesla

Nadeem Mohammad, posted Sep 13 2017

Avita Systems, a GE Venture, turned to NVIDIA DGX Systems to enable advanced robotic inspection and automated defect recognition services across the oil and gas, transportation, and energy industries.

Read more

New Translator Provides More Human-Like Translations

News, Cluster/Supercomputing, cuDNN, GeForce, Machine Learning & Artificial Intelligence, Media & Entertainment, Tesla

Nadeem Mohammad, posted Aug 31 2017

Germany-based startup DeepL launched a neural machine translator that was preferred by professional (human) translators by a 3-to-1 margin over similar tools.

Read more

Classifying Tattoos with Neural Networks

Features, Research, Cloud, cuDNN, DIGITS, Image Recognition, Machine Learning & Artificial Intelligence, Media & Entertainment, Tesla

Nadeem Mohammad, posted Aug 29 2017

With nearly 1.5 billion monthly visitors and 346,000 pictures of tattoos, Tattoodo is taking advantage of deep learning to help categorize the growing number of uploaded images.

Read more

Transform Flat Images Into High-Resolution 3D Models

Research, Computer Aided Design (CAD), cuDNN, GeForce, Higher Education/Academia, Machine Learning & Artificial Intelligence, Tesla

Nadeem Mohammad, posted Aug 24 2017

Researchers from University of California, Berkeley developed a deep learning-based method that creates a 3D reconstruction from a single 2d color image.

Read more