Communications of the ACM
Nc State to Form Nsf-Funded Center For Advanced Electronics Through Machine Learning With iuc and Georgia Tech
North Carolina State University, the University of Illinois at Urbana-Champaign, and the Georgia Institute of Technology are forming the Center for Advanced Electronics through Machine Learning to accelerate the design and verification of microelectronic
Credit: NCSU News
North Carolina State University (NCSU), the University of Illinois at Urbana-Champaign, and the Georgia Institute of Technology (Georgia Tech) are forming the Center for Advanced Electronics through Machine Learning (CAEML) to accelerate the design and verification of microelectronic circuits and systems, which should reduce the development costs and time to market for manufacturers of microelectronic products.
The center is funded for five years via the U.S. National Science Foundation's Industry/University Cooperative Research Centers program. It aims to speed up advances by leveraging machine learning techniques to develop new models for electronic design automation (EDA) tools.
"We're creating models that help deal with these complexities, so that when we design chips, we design them to work the first time," says NCSU professor Paul Franzon.
Researchers want to overcome the current limitations of chip manufacturing by employing behavioral models, which examine the output of a chip instead of the internal processes described by physical models.
The CAEML team will create a systematic method for generating behavioral models, drawing on deep networks, associative memories, and other research areas within the field of machine learning.
"With the interface between the chip and the package disappearing through integration, such as system-in-package technologies, systems need to be designed, modeled, and optimized holistically," says Georgia Tech professor Madhavan Swaminathan.
From NCSU News
View Full Article
Abstracts Copyright © 2016 Information Inc., Bethesda, Maryland, USA
No entries found