The U.S. Department of Energy (DOE) announced a plan to provide $2 million for basic research to advance neuromorphic computing.
Neuromorphic computing encompasses a range of different approaches to developing computing software and hardware that seek to mimic the neuron and synapse structure of the human brain. It offers the potential of both more powerful and sophisticated problem-solving as well as more energy-efficient computing than today’s computers.
As a computational system, the human brain is not only uniquely complex but also roughly a million times more energy-efficient than the most advanced supercomputers in existence today.
“As we look beyond the emerging generation of exascale computers and beyond Moore’s Law, neuromorphic computing could play a significant role in helping to define the future of high-performance computing systems,” said Dr. Chris Fall, Director of the DOE Office of Science. “It’s important that U.S. scientists probe these possibilities so that we can lay the groundwork for the coming generation of computational tools.”
The current initiative will support high-risk, high-reward research aimed at developing brain-inspired neuromorphic computing software tools and techniques as well as energy-efficient hardware. The aim is to create computing environments that will help accelerate scientific research while advancing the development of neuromorphic approaches to computation.
Applications will be open to universities, national laboratories, industry, and nonprofits, with awards selected competitively based on peer review. Total planned funding will be $2 million in Fiscal Year 2020 dollars for projects of two years in duration.