Portland State University joins nationwide program to develop brain-inspired computing
Portland State University will join seven other universities in forming a research center for brain-inspired computing – a set of technologies that has the potential to enable computers to do tasks that, as of now, are uniquely human.
The center will be headed by Purdue University in West Lafayette, Ind., but will include Portland State as well as Arizona State University, Georgia Institute of Technology, Pennsylvania State University, Princeton University, University of Pennsylvania, and University of Southern California.
The Center for Brain-inspired Computing Enabling Autonomous Intelligence, or C-BRIC, is a five-year project supported by $27 million in funding from the Semiconductor Research Corp (SRC) via their $200 million Joint University Microelectronics Program, which provides funding from a consortium of industrial sponsors as well as from the Defense Advanced Research Projects Agency (DARPA).
Portland State will receive $1.4 million of the total, most of which will be used to pay student researchers, according to Christof Teuscher, Maseeh professor in PSU's Maseeh College of Engineering and Computer Science.
Teuscher and fellow PSU engineering professor Dan Hammerstrom will head the PSU portion of the nationwide center.
"We are in a unique position in providing very special, highly optimized architectures that combine nature-inspired software and hardware," Teuscher said. "By nature-inspired, I mean that nature and the human brain do some things really well – like recognizing patterns and images. Machines are notoriously bad at that, so we are trying to figure out how the brain operates so some of that can be translated to computing."
Things like improved pattern and image recognition are important for developing intelligent autonomous systems such as drones and personal robots capable of operating without human intervention, Teuscher said.
"With the possibility of Moore's Law ending in the next decade, the entire industry is now focused on new kinds of computational models. Biologically inspired computing is particularly promising direction for future semiconductor systems," Hammerstrom, said.
Moore's law refers to the exponential growth of computing capacity that has been a part of the high-tech industry since the 1970s.
"The center's goal is to develop neuro-inspired algorithms, architectures and circuits for perception, reasoning and decision-making, which today's standard computing is unable to do efficiently," said Kaushik Roy, an electrical and computer engineering professor at Purdue who will lead the center.
Efficiency here implies energy use. For example, while advanced computers such as IBM's Watson and Google's AlphaGo have beaten humans at high-level cognitive tasks, they also consume hundreds of thousands of watts of power to do so, whereas the human brain requires only around 20 watts.
Teuscher runs the interdisciplinary Teuscher Lab at PSU, which uses aspects of computer science, computer engineering, physics, biology, complex systems science, and cognitive science to the study and the design of next generation computing.
Hammerstrom, whose research interests include biologically inspired information engineering on the molecular scale, has been a PSU professor since 2005, and spent four years as a DARPA program manager.
"This center will open bold new avenues for our research," Teuscher said. "The beauty of centers such as this, which involves other universities, is that it creates something bigger than the sum of their parts."