Neuromorphic computing promises to further accelerate the rapid progress that neural networks have made over the past 10 years. Josephson junctions and single flux quantum circuits form a natural neuromorphic technology with single flux quantum pulses and superconducting transmission lines simulating action potentials and axons. Josephson junctions consist of superconducting electrodes with nanoscale barriers that modulate the coupling of the complex superconducting order parameter across the junction. The coupling across a junction can be controlled and modulated by incorporating nanoscale magnetic structure in the barrier. The magnetic state of embedded nanoclusters can be changed by applying small currents or field pulses, enabling both unsupervised and supervised learning. The advantage of this magnetic/superconducting technology is that it combines natural spiking behavior and plasticity in a single nanoscale device and is orders of magnitude faster and lower energy than other technologies. Maximum operating frequencies are above 100 GHz, while spiking and training energies are ~10-20 J, 10-18 J, respectively. This combination of high-speed and low-power opens the possibility of scaling to networks that are more powerful than can be achieved with modern CMOS.
Sponsored by the NIST Seminar Series on Artificial Intelligence & Machine Learning and the NSCI Symposium Series
10:30-11:30 ET (NIST Gaithersburg, Lecture Room A)
8:30-9:30 MT (VTC to Boulder Room 1-4549)
To Join the meeting via Bluejeans, go to www.bluejeans.com, click “Join Meeting” (located in the upper right
corner) and enter the meeting ID.
Meeting ID: 908 546 723
Michael Schneider, Ph.D., Physicist
NIST, Quantum Electromagnetics Division, Boulder, CO
Michael Schneider is a Physicist at the National Institute of Standards and Technology in Boulder Colorado. He received his B.S. in physics from the University of Michigan in 1998 and his Ph.D. in physics from the University of Wisconsin in 2003. He has 15 years of research experience in experimental magnetism and spintronics. He has 8 years of research experience in experimental superconductivity and has spent the last 4 years working at the intersection of these fields. His current research is focused on novel ferromagnetic – superconducting devices and their applications including developing spiking neural networks with hybrid Josephson junction devices