Highlighting the key role GPUs will play in creating systems that understand data in human-like ways, Rob High, IBM Fellow, VP and chief technology officer for Watson, will deliver a keynote at our GPU Technology Conference, in Silicon Valley, on April 6.
Five years ago, Watson grabbed $1 million on Jeopardy!, competing against a pair of the TV quiz show’s top past winners. Today, IBM’s Watson cognitive computing platform helps doctors, lawyers, marketers and others glean key insights by analyzing large volumes of data.
High will join a lineup of speakers at this year’s GTC that includes NVIDIA CEO Jen-Hsun Huang and Toyota Research Institute CEO Gill Pratt, who will all highlight how machines are learning to solve new kinds of problems.
Fueling an AI Boom
Watson is among the first of a new generation of cognitive systems with far-reaching applications. It uses artificial intelligence technologies like image classification, video analytics, speech recognition and natural language processing to solve once intractable problems in healthcare, finance, education and law.
GPUs are at the center of this artificial intelligence revolution (see “Accelerating AI with GPUs: A New Computing Model”). And they’re part of Watson, too.
IBM announced late last year that its Watson cognitive computing platform has added NVIDIA Tesla K80 GPU accelerators. As part of the platform, GPUs enhance Watson’s natural language processing capabilities and other key applications. (Both IBM and NVIDIA are members of the OpenPOWER Foundation. The open-licensed POWER architecture is the CPU that powers Watson.)
GPUs are designed to race through a large number of tasks at once, something called parallel computing. That makes them ideal for many of the esoteric mathematical tasks that underpin cognitive computing, such as sparse and dense matrix math, graph analytics and Fourier transforms.
NVIDIA GPUs have proven their ability to accelerate applications on everything from PCs to supercomputers using all these techniques. Bringing the parallel computing capabilities of GPUs to these compute-intensive tasks allows more complex models to be used, and used quickly enough to power systems that can respond to human input.
The capabilities brought to Watson from GPUs are key to understanding the vast sums of data people create every day — a problem that High and his team at IBM set out to solve with Watson.
With structured data representing only 20 percent of the world’s total, traditional computers struggle to process the remaining 80 percent of unstructured data. This means that many organizations are hampered from gathering data from unstructured text, video and audio that can give them a competitive advantage.
Cognitive systems, like Watson, set out to change that by focusing on understanding language as the starting point for human cognition. IBM’s engineers designed Watson to deal with the probabilistic nature of human systems.
Dive in at Our GPU Technology Conference
Our annual GPU Technology Conference is one of the best places to learn more about Watson and other leading-edge technologies, such as self-driving cars, artificial intelligence, deep learning and virtual reality.
To register for the conference, visit our GTC registration page.