In this video from SC16, Roy Kim from Nvidia describes how the company is bringing in a new age of AI with accelerated computing for Deep Learning applications.
“Come join NVIDIA at SC16 to learn how AI supercomputing is breaking open a world of limitless possibilities. This is an era of multigenerational discoveries taking place in a single lifetime. See how other leaders in the field are advancing computational science across domains, get free hands-on training with the newest GPU-accelerated solutions, and connect with NVIDIA experts.”
Deep learning is the fastest-growing field in artificial intelligence, helping computers make sense of infinite amounts of data in the form of images, sound, and text. Using multiple levels of neural networks, computers now have the capacity to see, learn, and react to complex situations as well or better than humans. This is leading to a profoundly different way of thinking about your data, your technology, and the products and services you deliver.
NVIDIA has been a pioneer in accelerating deep learning and has been developing deep learning software, libraries and tools for a number of years. Today’s deep learning solutions rely almost exclusively on NVIDIA GPU-accelerated computing to train and speed up challenging applications such as image, handwriting, and voice identification. Deep learning systems with NVIDIA GPUs offer several advantages:
Accelerated DNN and Training Performance. NVIDIA GPUs excel at parallel workloads and speed up networks by 10-75x compared to CPUs, reducing each of the many data training iterations from weeks to just days. In fact, in the last year, GPUs have sped up training deep neural networks (DNNs) by as much as 12x.
Fast AI Application Development
AI innovation is happening at breakneck pace. Today, computers are not only learning, but thinking for themselves. This is opening fantastic opportunities in applications like robots, medicine, and self-driving cars. You can quickly design and deploy deep learning applications to take advantage of these incredible breakthroughs.
Whether you want to customize, build your own or simply “plug and play”, we have you covered. NVIDIA’s GPUs, built for deep learning, are available in desktops, notebooks, servers and supercomputers around the world, as well as in cloud services from Amazon, IBM and Microsoft. Our supporting software technologies and deep learning expertise ensures your workflow—training, deployment, or both—run smoothly.
