Professor Joshua Yang of the Electrical and Computer Engineering (ECE) Department was a co-principal investigator on a multi-disciplinary research team from UMass Amherst, UCLA, Stanford, the University of Michigan, and the University of Tennessee that was awarded a $7.5-million grant ($1 million to UMass Amherst) from the Department of Defense (DoD) for a study of brain-inspired memristive networks. Yang’s grant was one of 24 multidisciplinary university research initiative (MURI) awards selected from 295 proposals this year.
This is the second MURI project awarded to UMass on memristor studies after the first one was awarded to Professor Qiangfei Xia of ECE in 2011.
The project that Yang and colleagues are doing for the DoD, titled “Brain-Inspired Networks for Multifunctional Intelligent Systems in Aerial Vehicles,” will lead to platforms for machine learning from “big data” with speed, power efficiency, and memory capacity significantly superior to digital computers.
In addition, embedded synstor and neuristor integrated circuits (SNICs) will permit the establishment of intelligent behaviors in mobile systems for complex and dynamically changing environments. The principal investigator for the project is Professor Yong Chen of UCLA.
With this newest grant, Yang and Xia have already secured four grants totaling about $2 million in the first quarter of 2019 to support their memristor-related research.
“Together with these $2 million,” explains Yang, “Qiangfei and I have attracted about $7 million in extramural research funding on memristor-related studies in the last four years, leading to a number of significant progresses published in about 20 papers in Nature research journals and establishing UMass a well-recognized institution in neuromorphic computing with emerging devices.”
As the abstract for Yang’s new DoD project explains, “Computers have led to an information revolution and artificial intelligent systems that simulate the learning functions of the human brain. The world’s fastest supercomputer, Summit, may have a computing capacity comparable to that of the human brain. However, Summit consumes the equivalent power of 7,000 homes (~15 MW), and the brain only consumes the power of a light bulb (~20 W).”
According to Yang and Xia, computers execute algorithms on physically separated logic and memory units in digital serial mode, a factor which fundamentally restrains computers from handling “big data” efficiently in complex dynamic environments and limits the development of emerging intelligent systems such as self-piloted unmanned aerial vehicles. By contrast, the brain simultaneously processes and learns from “big data” via trillions of synapses and neurons in analog parallel mode and facilitates parallel processing and real-time learning with an energy efficiency more than five orders of magnitude superior to that of the supercomputer.
In this project, the abstract observes, the researchers plan to perform research on various devices, including synaptic resistors (synstors), memory resistors (memristors), and neuristors. In the process, they also plan “to emulate the analog short- and long-term memory, convolutional signal processing, and correlative learning functions of synapses and the nonlinear dynamic functions of neurons.”
In addition, the researchers say, “We will develop a SNIC that operates in analog parallel mode, facilitates processing and real-time learning, is more than six orders of magnitude more efficient than that of the supercomputer, and consumes a power of ~1 mW.”
The research team will also integrate multiple SNICs with distributed networks of sensors and actuators to demonstrate multifunctional intelligent systems with structural health-monitoring, automatic navigation, and real-time learning in self-piloted aerial vehicles.
Finally, according to the researchers, “We will also establish theoretical models for transforming intelligent functions of the brain to SNICs and intelligent systems.”
For this round of MURI awards, the DoD announced $169 million for 24 research teams across 73 U.S. academic institutions pursuing basic research spanning multiple scientific disciplines. For a list of the winning teams, click here. (May 2019)