Mark Stiles

Abstract: Computers, originally designed to do precise numerical processing, are now widely used to do more
cognitive tasks. These include categorical challenges like image and voice recognition, as well as robotic tasks like
driving a car and making real-time decisions based on sensory input. While the human brain does not do precise
numerical processing well, it excels at these other tasks, leading researchers to look to the brain for inspiration on
efficient ways to engineer cognitive computers. Of particular interest are energy and space optimization. Computers
can now perform many of these cognitive tasks as well as humans, and often faster, but at the cost of much higher
total energy consumption and much greater space. Some improvements are being found from algorithms that are
more brainlike, and some from novel electronic devices that emulate features of the brain. However, the greatest
progress can be found by working simultaneously across the computational stack integrating both.
Magnetic tunnel junctions have several features that make them attractive potential devices for these applications.
One feature is that they are already integrated into fabrication plants for complementary-metal-oxide-semiconductor
(CMOS) integrated circuits. They can be readily integrated with existing CMOS technology to take advantage of its
many capabilities. Another feature is that they are multifunctional. With only slight changes in fabrication details,
they can be modified to provide non-volatile memory, truly random thermal fluctuations, or gigahertz oscillations.
Magnetic tunnel junctions can be used as a memory to store synaptic weights, but when the weights change too
frequently the energy cost of repeatedly writing them becomes inefficient. Reducing the retention time of the
memory reduces the cost of writing them, leading to a trade-off between energy efficiency and reliability. The
seemingly random patterns of neural spike trains have inspired a number of computational approaches based on the
random thermal fluctuations of superparamagnetic tunnel junctions. I discuss some of these approaches and the
design choices we have made in implementing neural networks based on superparamagnetic tunnel junctions.

Biography:

Mark Stiles is a NIST Fellow in the Alternative Computing Group in the Physical Measurement Laboratory. He
received a M.S./B.S. in Physics from Yale University, and M.S. and Ph.D. degrees in Physics from Cornell University.
Following postdoctoral research at AT&T Bell Laboratories, he joined the research staff at NIST. Mark's research,
published in over 160 papers, has focused on the development of a variety of theoretical methods for predicting the
properties of magnetic nanostructures and has recently shifted to neuromorphic computing. He has helped organize
numerous conferences and has served the American Physical Society on the Executive Committee of the Division of
Condensed Matter Physics and as Chair and on the Executive Committee of the Topical Group on Magnetism. He has
also served as a Divisional Associate Editor for Physical Review Letters, served on the Editorial Board of Physical
Review Applied, and is an Associate Editor for Reviews of Modern Physics. Mark is a Fellow of the American Physical
Society and has been awarded the Silver Medal from the Department of Commerce.

Address:United States