Scientists develop fully integrated memristor chip with low energy consumption
This photo taken on Jan. 18, 2020 shows the research team led by professor Wu Huaqiang (C) at Tsinghua University in Beijing, capital of China. (Tsinghua University/Handout via Xinhua)
BEIJING, Oct. 11 (Xinhua) -- Chinese scientists have developed a fully integrated memristor chip with improved learning ability and low energy cost, according to a study recently published in the journal Science.
With artificial intelligence (AI) technology profoundly changing the way of production and life, learning becomes highly important for edge intelligence devices in order to adapt to different application scenarios.
However, current technologies for training neural networks require moving extensive data between the processor chip and off-chip main memory, which incurs massive energy consumption and hinders the learning process.
Based on 11 years of research, scientists from Tsinghua University developed a full-system-integrated chip consisting of multiple memristor arrays and all the necessary peripheral circuits to support complete on-chip learning.
"The chip integrates complete circuit modules to support autonomous learning, and it has successfully demonstrated various learning tasks including motion control, image classification and speech recognition," said Yao Peng, the co-first author of the study, from the School of Integrated Circuits, Tsinghua University.
According to the study, the chip can achieve autonomous learning with only about three percent of the energy consumption of the conventional application specific integrated circuits (ASIC) when running the same task.
The chip showed high energy efficiency and high accuracy in versatile AI tasks during the experiments, which can effectively strengthen the learning adaptability of intelligent devices in practical application scenarios, Yao said.
"This chip provides an innovative development path for AI hardware breakthroughs," said Gao Bin, a professor at Tsinghua University.
This study is an important step toward future chips with high energy efficiency and learning capabilities, said Wu Huaqiang, dean of the university's school of integrated circuits.
"We hope our findings will accelerate the development of future smart edge devices that can adapt to different application scenarios and owners," Wu added.
This image shows the fully integrated memristor chip and its test system. (Tsinghua University/Handout via Xinhua)
Related articles
‘The Blue Angels,’ filmed for IMAX, puts viewers in the ‘box’ with the elite flying squad
If you’re looking for a little bit of that “ Top Gun: Maverick ” spectacle and thrill at the movie t2024-05-21Community housing developments stall as government funding not guaranteed
The Salvation Army is ready to build about 70 homes, but has been told the applications cannot be pr2024-05-21100 days since Hamas attacked Israel, triggering war in Gaza
Photo: GIL COHEN-MAGEN / AFP2024-05-21EDITORIAL: Reform of WTO key to regaining dispute
Protecting a rules-based trade order is more crucial than ever as divisions that widen between count2024-05-21Mohammad Mokhber: Who is Iran’s acting president?
DUBAI, United Arab Emirates (AP) — Iran’s first Vice President Mohammad Mokhber was appointed as act2024-05-21Hurricanes haka: A brief history of protests in sport
From top left: Bryan Williams and Bob Burgess, Josh Kronfeld, Tommie Smith and Darren Waller. Photo:2024-05-21
atest comment