Accelerating research and adoption of breakthrough AI systems
The Intel Neuromorphic Research Community (Intel NRC) is an ecosystem of academic groups, government labs, research institutions, and companies around the world working with Intel to further neuromorphic computing and develop innovative AI applications.
With Intel's near-commercial neuromorphic computing systems, Intel NRC members have the tools to develop and test proof-of-concepts that collaboratively advance the field of neuromorphic computing.
Enable Commercial Applications
The Intel NRC is accelerating the adoption of neuromorphic technology by developing, prototyping, and scaling applications built on Intel's neuromorphic systems.
As neuromorphic computing progresses toward commercialization, the Intel NRC is committed to setting benchmarks to measure the technology's value in an open, collaborative way.
What We Offer
Vibrant Research Ecosystem
The Intel NRC offers access to a global network of researchers that regularly share insights from their work to collaboratively break through challenges and advance the field.
Access to Small and Large-Scale Neuromorphic Systems
The Intel NRC provides members cloud-based access to both small and large-scale neuromorphic computing systems to further development of applications with impact from the edge to the data center.
The Intel NRC offers funding for universities around the world to pursue their research plans.
The Intel Neuromorphic Research Community is a global network of more than 75 research groups who are committed to delivering on the promise of neuromorphic computing to make the technology a commercial reality.
With the Loihi chip we've been able to demonstrate 109 times lower power consumption running a real-time deep learning benchmark compared to a GPU, and 5 times lower power consumption compared to specialized IoT inference hardware. Even better, as we scale the network up by 50 times, Loihi maintains real-time performance results and uses only 30 percent more power, whereas the IoT hardware uses 500 percent more power and is no longer real-time.
Intel's Loihi neuromorphic processors have enormous potential to deliver new capabilities in AI and Edge computing. The flexibility in programming, ready access to the cloud-based resources and connections to a robust third-party neuromorphic computing ecosystem are all key factors industrial companies, like GE, require to transform complex industrial systems and networks.
Loihi allowed us to realize a spiking neural network that imitates the brain's underlying neural representations and behavior. The SLAM solution emerged as a property of the network's structure. We benchmarked the Loihi-run network and found it to be equally accurate while consuming 100 times less energy than a widely used CPU-run SLAM method for mobile robots.
Membership in the Intel Neuromorphic Research Community is open to all qualified academic, corporate, and government research groups around the world, at no charge. If you are interested in joining the Intel NRC, please email us introducing yourself and your research interests.
While members are encouraged to share the code, algorithms, and designs they develop using Intel's neuromorphic platforms, free sharing of intellectual property is not required. One of Intel's long-term goals is to nurture a commercial neuromorphic ecosystem, and as such, members may retain full proprietary ownership of any inventions that come from their work with Loihi.
Members of the Intel NRC
Members of the Intel Neuromorphic Research Community share research progress and results at the group’s fall workshop in Graz, Austria. (Credit: Intel Corporation)
Intel's self-learning neuromorphic research chip, codenamed Loihi. Loihi serves as the foundation for all neuromorphic systems available to the Intel NRC. (Credit: Intel Corporation)
Researchers at the 2019 Telluride Neuromorphic Cognition Engineering Workshop worked on automating Western Sydney University’s foosball table under Loihi control, operating on visual input from event-based cameras. Foosball offers an excellent test for rapid closed-loop sensing, planning, and control algorithms, a sweet spot for neuromorphic technology. (Credit: Sumit Bam Shrestha)