Image: Qilian Liang
see After

Credit: UT Arlington

A University of Texas at Arlington researcher has received a three-year grant worth nearly $600,000 from the National Science Foundation to make technology used with artificial intelligence (AI) faster and more economical in energy so that it can be used in real time.

Electrical Engineering Professor Qilian Liang will design deep learning hardware accelerators through devices, circuits and algorithms to create deep generative AI models with simpler design and architecture. Deep generative AI uses statistics and probability to produce scalable patterns of complex data, including images, text, and data. Liang’s research should yield orders of magnitude improvements in power consumption and speed.

Chenyun Pan, assistant professor of electrical engineering, is co-principal investigator of the project

“We will look at architecture, hardware and software to make the process of AI technology much faster so that it can be implemented in real time and increase its energy efficiency,” Liang said. “Beyond the obvious computer applications, this technology could also find its way into the field in robots, autonomous driving, and even the process of creating real-time press releases.”

Liang will simplify the architecture used to design the hardware to increase computing speed. He will also create an algorithm to determine if implementing AI can cost less and design more efficient circuits and hardware to save money and enable faster computation.

The team will focus on three types of deep generative models:

  • Vision transformer-based generative modeling uses a transformer architecture on patches of an image to improve image recognition. If the AI ​​can use environmental cues to determine what it sees rather than having to sort through many images, it will require less energy and time.
  • Hidden generative modeling hides data that isn’t useful for the task at hand, reducing the amount of data the AI ​​has to sort through. Later, this masked data can be retrieved and used to fill in gaps that could enable earlier decision making.
  • Cross-modal generative modeling uses two types of models to simultaneously sort multimodal data and identify what is useful and what is not.

“As AI technology advances, the need for it to be faster and more energy efficient becomes greater,” said Diana Huffaker, chair of the electrical engineering department. “Dr. Liang’s work will enable greater innovation in the future by removing some of the current limitations of this technology.

Liang joined UTA in 2002. He was made a Fellow of the Institute of Electrical and Electronics Engineers in 2016 due to his contributions to computer intelligence.

  • Written by Jeremy Agor, College of Engineering

Disclaimer: AAAS and EurekAlert! are not responsible for the accuracy of press releases posted on EurekAlert! by contributing institutions or for the use of any information through the EurekAlert system.