Chinese researchers have unveiled a new computer chip inspired by the human brain that they say could revolutionize artificial intelligence applications such as self-driving cars and smartphones.
The Tianmoc chip is the brainchild of a team from Tsinghua University’s School of Precision Engineering, whose research published Thursday in the journal Nature details a “dual-pathway complementary brain-like perception chip” designed to mimic the way the human visual system processes information.
“This is a fundamental breakthrough for China in both brain-like computing and brain-like perception,” said Shi Luping, a professor and co-author of the study.
Tianmoc tackles a key AI challenge: visual recognition in complex environments. Traditional chips often struggle with extreme conditions such as sudden light changes and strong interference. However, Tianmoc is designed to handle these scenarios efficiently, delivering high-speed, high-precision, high-dynamic-range visual processing with low power consumption.
“This paradigm is based on the fundamental principles of the human visual system,” Shi said. “It decomposes visual information in an open environment into a representation based on visual primitives. By organically combining these primitives, the model mimics the characteristics of the human visual system, forming two complementary and comprehensive visual perception paths.”
“Not only does it overcome the performance bottlenecks of the traditional paradigm, but it also efficiently handles a variety of extreme scenarios to ensure system stability and safety.”
The chip’s potential uses go beyond self-driving cars and robots: Shi expects that as production costs fall, Tianmoc will eventually see it adopted into everyday devices like smartphones, providing new capabilities.
The research builds on the team’s previous work on another brain-inspired chip, Tianjic, which appeared on the cover of Nature magazine in 2019. With the introduction of Tianmoc, the researchers believe they are creating a comprehensive “brain-like intelligence ecosystem” that could pave the way towards artificial general intelligence, a type of AI that can mimic human-like learning and reasoning.
“We are on a completely unique technology path, which is original,” Shi said. “This will solve many difficult problems, provide new development perspectives and potentially lead to new applications.”
