Accelerating deep learning using the cloud

As part of its exhibition at GTC 2016, the world’s largest GPU conference, BIOS IT is showcasing BIOS ANNA, which the company claims is the world’s fastest deep learning training accelerator.

The artificial neural network accelerator features multiples of the fast NVIDIA Tesla GPU accelerator, which is purpose-built to dramatically reduce training time, in some cases up to 20-fold, the company claims. Recent benchmarks have supported this claim by reporting a reduction in training time from five days to six hours when testing the accelerator against a standard dual CPU server, according to the company.

Deep learning is the fastest-growing field within the general processing unit (GPU) sphere. It is used in the research community and in industry to help solve many big data problems such as computer vision, speech recognition, and natural language processing. Accelerated training time equates to faster deployment.

For more information, go to