Chinese transistor breakthrough paves way for future AI chips

Chinese researchers have achieved a breakthrough in ferroelectric transistors (FeFETs), overcoming long-standing limitations of traditional versions and paving the way for large-scale applications. These transistors function similarly to neurons in the human brain, integrating memory and processing in a single unit to reduce data transfer time.

Researchers at Peking University have achieved this feat in ferroelectric transistors (FeFETs), described as smaller, faster, and smarter for future AI chips. The breakthrough is said to overcome long-standing limitations of traditional ferroelectric transistors, ‘paving way for large-scale application’.

FeFETs function similarly to neurons in the human brain as they integrate memory and processing in a single unit, thereby reducing the time lost in data transfer. Key terms include Peking University, ferroelectric memory chips, Professor Qiu Chenguang, ferroelectric transistor, Science Advances, ferroelectric layer, nanogate FeFET, Science and Technology Daily, transistor, Professor Peng Lianmao, semiconductor materials, FeFETs, AI chips, Chinese Academy of Sciences, and sub-nanometer node chips.

The research was published in Science Advances, with contributions from the Chinese Academy of Sciences.

ተያያዥ ጽሁፎች

Elon Musk announces Tesla AI5 chip nearing completion at a conference, with roadmap visuals of AI chips, cars, and robots on screen.
በ AI የተሰራ ምስል

Tesla's AI5 chip design nears completion as Musk outlines rapid roadmap

በAI የተዘገበ በ AI የተሰራ ምስል

Elon Musk announced that Tesla's next-generation AI5 chip is almost complete, with early work already underway on AI6 and plans for a nine-month development cycle for future iterations. The chips are expected to become the highest-volume AI processors globally, powering vehicles, robots, and more. This update highlights Tesla's aggressive push in AI hardware for autonomy and beyond.

Researchers at Korea University have developed a dual-output artificial synapse to boost the energy efficiency of multitasking AI systems, the university announced. The device emits both electrical and optical signals simultaneously to enable parallel processing. Tests showed up to 47 percent faster computation and energy use reduced by as much as 32 times compared to conventional GPU hardware.

በAI የተዘገበ

Researchers from Purdue University and the Georgia Institute of Technology have proposed a new computer architecture for AI models inspired by the human brain. This approach aims to address the energy-intensive 'memory wall' problem in current systems. The study, published in Frontiers in Science, highlights potential for more efficient AI in everyday devices.

A team of scientists has developed a new method to manipulate quantum materials using excitons, bypassing the need for intense lasers. This approach, led by the Okinawa Institute of Science and Technology and Stanford University, achieves strong Floquet effects with far less energy, reducing the risk of damaging materials. The findings, published in Nature Physics, open pathways to advanced quantum devices.

በAI የተዘገበ እውነት ተፈትሸ

Researchers have developed a paper-thin brain implant called BISC that creates a high-bandwidth wireless link between the brain and computers. The single-chip device, which can slide into the narrow space between the brain and skull, could open new possibilities for treating conditions such as epilepsy, paralysis, and blindness by supporting advanced AI models that decode movement, perception, and intent.

Elon Musk has stated that Tesla's next-generation AI5 chip is nearly complete in design, six months after claiming it was finished. Samsung is preparing its Texas factory for trial operations to support AI5 production later in 2026. The chip will be manufactured by both Samsung and TSMC using advanced processes.

በAI የተዘገበ

Rising talent in micron-precision 3D printing, Xu Zhenpeng, announced on social media his move from a California startup to an academic position in Shanghai, China. Previously, he led a team developing 3D printing techniques to make chip production faster and cheaper than conventional multimillion-dollar machines.

 

 

 

ይህ ድረ-ገጽ ኩኪዎችን ይጠቀማል

የእኛን ጣቢያ ለማሻሻል ለትንታኔ ኩኪዎችን እንጠቀማለን። የእኛን የሚስጥር ፖሊሲ አንብቡ የሚስጥር ፖሊሲ ለተጨማሪ መረጃ።
ውድቅ አድርግ