appConfigEntityId

bodyType

customContents

entityId

entityUuid

isVideo

articlePageQuery

article

articleSchemaContent

content

hooksArticlePageAdvertisementConfigArticle

hooksArticlePageFloatingButtonConfigArticle

appConfig

filter

json

liveArticle

Holly Chik

Chinese scientists say they have developed a tiny computer chip capable of modelling complex brain structures in real time.
According to its developers, this chip could not only transform diagnostics and treatment for conditions such as Alzheimer’s disease, but also boost the performance of brain-machine interfaces and assist surgeons.
Researchers from Peking University and the Chinese Academy of Sciences reported the breakthrough in a peer-reviewed study published in Science on Thursday, detailing a 40-nanometre memory chip with an integrated artificial neural network.
The device overcomes long-standing computational limits, enabling it to reconstruct complex brain surfaces in less than half a second – making it 50 to 478 times faster than state-of-the-art Nvidia A100 graphics processing unit (GPU) systems, according to the team.
Lead author Yang Yuchao, a professor at Peking University’s school of integrated circuits and deputy dean for its school of electronic and computer engineering, told state-run Guangming Daily that the chip could accurately render the brain’s folds for medical applications.
“This breakthrough opens up new possibilities for brain-computer interfaces and the diagnosis and treatment of brain diseases,” he said. “In the future, personalised and dynamic digital brain twins will become possible.”
“It also provides a hardware foundation that can operate in real time for intraoperative neuronavigation [a navigation system for surgery], early screening for Alzheimer’s disease and personalised interventions,” Yang added.


The human brain has folds to increase its surface area, allowing the organ to pack billions of neurons within the skull’s physical limits.
Previously, reconstructing these complex grooves in real time required expensive, large-scale equipment for lengthy calculations.
Standard computer architecture faces a bottleneck because storage and processing units are kept separate. Data must travel constantly between the memory unit and the processor, resulting in significant latency and high power consumption.
The Chinese team solved this by integrating a neural dynamical system into a computing-in-memory architecture. This design performs data storage and computation within the same memory array.
They took a major flaw in phase-change memristors or next-generation memory chips – a glitch called “conductance drift” that usually makes data unstable – and turned it into a powerful tool for computing.
In an accompanying analysis in Science, two researchers at the Juelich Research Centre in Germany, who were not involved in the study, described performing data storage and computation in the same memory array as “analogous to processing raw milk on a dairy farm instead of transferring it to a factory”.
“The platform can perform high-fidelity calculation with a millisecond-scale latency, establishing a pathway toward real-time computation in clinical imaging, robotics and embodied intelligence,” they added.
“The reduction in latency demonstrated by [the research team] establishes a new hardware paradigm for topology-preserving neural dynamical computation, which could enable real-time cortical surface tracking during neurosurgery and could be integrated into clinical decision-making.”


China tests first practical submarine solar power plant at 10-metre depth in the open sea

Rare earth exposure can triple low birthweight risk: Chinese study

China must enforce high standards of integrity for scientists

Is China’s fabled Empress Dowager Huayang buried near an airport? A study says yes

Science

Chinese scientists’ brain-mimicking chip ‘up to 478 times faster than Nvidia A100 GPU’

The breakthrough “opens up new possibilities for brain-computer interfaces and the diagnosis and treatment of brain diseases”, lead author of study published in Science says. Photo: Shutterstock

Chinese scientists create record-smashing brain implant electrode array thinner than hair

In animal trials, a new flexible brain implant successfully recorded neural activity with unprecedented long-term clarity and remained safely functional inside the body for 18 months. Photo: Shutterstock

The cortical electrode arrays commonly used today, typically made of platinum or platinum-iridium alloys, offer excellent conductivity but are far stiffer than neural tissue. Photo: Shutterstock

Cancer-on-a-chip pioneer Chen Weiqiang returns to China from New York University

Chen Weiqiang. Photo: Handout

Chen Weiqiang has joined the school of biomedical engineering at Nanjing University as a distinguished professor. Photo: Handout

Chen Weiqiang (right) has left his position as tenured professor of mechanical and biomedical engineering at New York University. Photo: Handout

Soft brain chip could help solve Neuralink’s big implant challenge

3D semiconductors enable 3D spatial connections. Photo: Dreamstime/TNS

‘Brain-like’ AI said to run 100 times faster on ultra-long tasks using Chinese chips

A digital rendering of a brain. (Shutterstock)

SpikingBrain 1.0 can learn from less than 2 per cent of the training data needed by other systems while staying fast and efficient, according to its developers. Photo: Handout

News

China

New chip performs data storage and computation in a single memory array, enabling real-time modelling of complex brain structures, team says


New chip performs data storage and computation in a single memory array, enabling real-time modelling of complex brain structures, team says.


Semiconductors

Nvidia

Chinese Academy of Social Sciences

Peking University

Chinese scientists’ brain-mimicking chip ‘up to 478 times faster than Nvidia A100 GPU’

.css-1c6uqr6{color:inherit;font-weight:inherit;font-size:inherit;font-family:inherit;line-height:inherit;overflow-wrap:break-word;}New chip performs data storage and computation in a single memory array, enabling real-time modelling of complex brain structures, team says

New chip performs data storage and computation in a single memory array, enabling real-time modelling of complex brain structures, team says