Intel has announced a collaborative research initiative to encourage experimentation with its Loihi neuromorphic test chip.
By Dr Michael Mayberry, chief technology officer for Intel, as well as senior vice-president and MD of Intel Labs, writes this report-back from the Neuro Inspired Computational Elements (NICE) workshop hosted by Intel.
Here’s a status of our neuromorphic computing efforts and details on this new research community.
Where We Are
Fabrication and packaging of our Loihi test chip was completed in early November, and we began power-on and validation.
We were pleased to find 100% functionality, a wide operating margin and few bugs overall.
Our small-scale demonstrations that we had prepared on our emulator worked as expected on the real silicon, though, of course, running orders of magnitude faster.
Our equivalent of a “Hello World” application is recognising a 3D object from multiple viewing angles, structured after the COIL-20 example from Columbia University.
As measured at our lab, this particular application uses less than 1% of Loihi, learns the training set in seconds and consumes tens of milliwatts.
We shared Loihi architectural details in a paper that IEEE Micro recently published, and we presented those details and several demos to NICE workshop attendees.
We have delivered the first developer systems to select research collaborators who are working on a variety of applications including sensing, motor control, information processing and more.
Software development tools remain one of our focus areas, and we’re looking forward to running much larger scale applications in conjunction with research collaborators.
As we learn more together, we expect progress to accelerate, and that’s where today’s announcement comes in.
Establishing the Intel Neuromorphic Research Community
We announced the formation of the Intel Neuromorphic Research Community (INRC) – our effort to create a network of collaborators spanning academic, government and industry research groups.
We invited workshop attendees to submit proposals under the following research vectors:
* Neuromorphic Theory: Abstracting neuroscience understanding and relating it to practical computational models.
* Spiking Neural Network Algorithms: Principled development of neural network dynamics, features and learning rules.
* Neuromorphic Applications: Systems and software that use Loihi and future Intel neuromorphic architectures to solve real-world problems.
* Programming Models: New paradigms for conceptualising and specifying the structure and emergent behaviour of neuromorphic systems.
* Event-Driven Sensing and Control Technologies: Novel and efficient approaches for interfacing spike-based computing systems with real-world data and systems.
Qualifying proposals may receive grants for their work as well as access to a software development kit and a Loihi test system.
Because we have a high demand for Loihi development systems, we are working to enable cloud access to a scalable, multiuser Loihi-based system, which we dub our Neuromorphic Research as a Service (NRaaS).
Community members will agree to share results with the goal of advancing neuromorphic computing and uncovering potential use cases for this nascent but promising field of computer science research. We will begin accepting initial proposals April 2.
We are excited by what this research and development work could mean for our Loihi test chip. With the collaboration of leading research institutes around the world, this chip can progress from a prototype to an industry-leading product over the coming years.
Indeed, the future is bright.