AI Models Microprocessor Performance in Real-Time
New algorithm predicts processor power consumption trillions of times per second while requiring little power or circuitry of its own
The IEEE will launch the new Transactions on Circuits and Systems for Artificial Intelligence (TCASAI) in September 2024
Yiran Chen, the John Cocke Distinguished Professor of Electrical and Computer Engineering at Duke University, will serve as the inaugural editor-in-chief of the new journal Transactions on Circuits and Systems for Artificial Intelligence (TCASAI) published by the Institute of Electrical and Electronics Engineers (IEEE).
The first ever IEEE periodical exclusively dedicated to AI hardware, the journal will focus on topics such as circuit and electronic system design, implementation and demonstration. The journal, which is set to launch this September, aims to offer a timely and important venue to fulfill the strong need of the IEEE communities in publishing research and technical contributions in the fast-growing field.
“The introduction of TCASAI will significantly promote AI hardware research and bolster the development of the relevant community,” Chen said.
John Cocke Distinguished Professor of Electrical and Computer EngineeringThe introduction of TCASAI will significantly promote AI hardware research and bolster the development of the relevant community
A leading pioneer in the field for two decades, Chen’s work in this field has historically focused on developing so-called “neuromorphic” computing hardware and capabilities. The approach hinges on a new computing device called a “memristor,” which is essentially a switch that can remember which electric state it was in even after its power is shut off.
In back-to-back papers that recently won “test of time” awards for their influence in the field, Chen and his co-authors proposed the hardware design for a robust memristor as well as a methodology for training machine learning algorithms called artificial neural networks with them. In combination, the two papers comprised a launchpad for future research in this promising form of artificial intelligence (AI) chips.
At Duke, Chen leads the National Science Foundation’s Athena AI institute focused on developing edge computing with groundbreaking AI functionality and hardware to provide previously impossible services at low cost. Bringing together a multidisciplinary team of scientists, engineers, statisticians, legal scholars, and psychologists from eight universities, Athena’s goal is to transform the design, operation, and services of future mobile devices and computing systems.
New algorithm predicts processor power consumption trillions of times per second while requiring little power or circuitry of its own
Ten years ago, three destined-to-be Duke engineers rethought the way data could be stored and computed
Duke professor Yiran Chen is the third faculty member in the Department of Electrical and Computer Engineering to capture the prestigious award