Fujitsu Touts Faster Deep Learning
Japan’s Fujitsu Laboratories Ltd. claims its latest artificial intelligence software enables the world’s fastest machine learning processing.
Japan’s Fujitsu Laboratories Ltd. claims its latest artificial intelligence software enables the world’s fastest machine learning processing.
Used in a 2,048 GPU network, the so-called deep learning system completed training calculations in less than 75 seconds—about 30% faster than the previous best. The gain was achieved in part by expanding computational volume per graphic processing unit used for image recognition, according to Fujitsu.
Deep learning is considered a key enabler for next-generation autonomous vehicles. The technology allows vehicles to quickly identify images/patterns and build a reference database that trains software to make decisions based on learned inputs and outcomes.
Fujitsu tested its system at Japan’s National Institute of Advanced Industrial Science and Technology. The technology was tested on Microsoft Corp.’s ResNet-50 deep-learning neural network.
RELATED CONTENT
-
Choosing the Right Fasteners for Automotive
PennEngineering makes hundreds of different fasteners for the automotive industry with standard and custom products as well as automated assembly solutions. Discover how they’re used and how to select the right one. (Sponsored Content)
-
Cobots: 14 Things You Need to Know
What jobs do cobots do well? How is a cobot programmed? What’s the ROI? We asked these questions and more to four of the leading suppliers of cobots.
-
Robotic Exoskeleton Amplifies Human Strength
The Sarcos Guardian XO Max full-body, all-electric exoskeleton features strength amplification of up to 20 to 1, making 200 pounds—the suit’s upper limit—feel like 10 pounds for the user.