Latest news with #NatureElectronics
South China Morning Post
06-07-2025
- Science
- South China Morning Post
Chinese team develops faster, more efficient data sorting system for AI and computing
Chinese scientists have developed a faster and more energy-efficient method to sort data, which could be used to overcome limitations in scientific computing, artificial intelligence, and hardware design. Advertisement Their new sorting system relies on memristors, an electronic circuit component with memory-like abilities, along with a sorting algorithm to enable more efficient data processing. The team built a memristor-based hardware sorting prototype to demonstrate tasks such as route finding and neural network inference, achieving both speed and energy efficiency improvements over traditional sorting methods. 'Sorting is a performance bottleneck in numerous applications, including artificial intelligence, databases, web search and scientific computing,' the team said in a paper published in the peer-reviewed journal Nature Electronics on June 25. Computing systems are typically based on Von Neumann architecture, which separates data storage – or memory – and processing, such as through the use of a central processing unit (CPU). Advertisement This has led to the Von Neumann bottleneck, a limit on the speed of data transfer between the main memory and processing unit. 'Sort-in-memory using memristors could help overcome these limitations, but current systems still rely on comparison operations so that sorting performance remains limited,' said the researchers from Peking University and the Chinese Institute for Brain Research.
South China Morning Post
18-02-2025
- Health
- South China Morning Post
Chinese scientists boost brain-computer link efficiency 100-fold, study shows
Chinese researchers say they have developed the world's first two-way adaptive brain-computer interface (BCI), boosting efficiency 100-fold and moving the technology a step closer towards practical everyday use. In a study published on Monday by Nature Electronics, the scientists said the system could eventually be integrated into portable and wearable BCI devices, making it suitable for consumer and medical applications. A schematic of the brain computer interface with the brain-memristor decoder co-evolution. Illustration: Nature Unlike traditional BCIs, which decode the brain's signals, the breakthrough enables the brain and device to learn from each other, delivering a stable performance over time, according to the Tianjin University and Tsinghua University researchers. 'Our work is the first to introduce the concept of brain-computer co-evolution and successfully demonstrate its feasibility, marking an initial step towards mutual adaptation between biological and machine intelligence,' said co-author Xu Minpeng from Tianjin University. BCI technology dates from the 1970s when scientists first showed that brain signals could be recorded and translated into commands, allowing users to control machines with their thoughts. While early research focused on helping people with disabilities, today's BCIs have expanded into a wide range of applications, from wearable devices for gaming to hands-free drone control. However, the one-directional nature of the technology has meant that BCI devices have been unable to provide feedback that helps the brain adjust and improve control over time. This limitation often causes performance to decline over extended use.
