Shulou(Shulou.com)12/24 Report--

CTOnews.com, December 23 (Xinhua)-- scientists have made another major breakthrough in the field of AI, with the advent of an AI synaptic transistor that mimics the human brain.

This AI synaptic transistor operates in a way similar to human cognition and can process and store information at the same time, marking a significant shift from traditional machine learning tasks to associative learning.

Image source: Xiaodong Yan / Northwestern University more importantly, this AI synaptic transistor can operate effectively at room temperature, has the advantages of fast operation, low energy consumption, and can retain information without power supply, so it has a broad application prospect.

The study was carried out by researchers at Northwestern University, Boston College and the Massachusetts Institute of Technology (MIT). In a press release, Professor Mark Hersam said:

The structure of the brain is fundamentally different from that of a digital computer.

In digital computers, data needs to move back and forth between microprocessors and memory, which is bound to consume a lot of energy and create bottlenecks when trying to perform multiple tasks at the same time.

In the human brain, memory and information processing are located in the same place and fully integrated, thus improving energy efficiency by several orders of magnitude. Our synaptic transistors also perform concurrent memory and information processing functions, which can more faithfully mimic the brain.

Hesam's team mainly used Moir é pattern to develop synaptic transistors.

CTOnews.com Note: Mohr pattern is a geometric pattern that occurs when two patterns are superimposed on each other. When two-dimensional materials are stacked, new properties appear, which do not exist in a single-layer structure. When these hierarchies are twisted to form a moire pattern, it is possible to reap unprecedented electronic properties.

In this new synaptic transistor, the researchers combine two different types of atomic-grade thin materials, bilayer graphene and hexagonal boron nitride. Graphene and hexagonal boron nitride are very similar in structure, but the differences between them are enough to produce an unusually strong moire effect to manipulate the electronic properties of the graphene layer.

This operation can be performed at room temperature to produce synaptic transistors that enhance neuromorphological function.

In the associative learning test, the AI transistor can compare "101" and" 111", distinguishing the latter from "000,000".

This ability to deal with complex and imperfect inputs is of great significance to real-world artificial intelligence applications.

CTOnews.com attached the reference address of the paper.

Yan, X., Zheng, Z., Sangwan, V.K. Et al. Moir é synaptic transistor with room-temperature neuromorphic functionality. Nature 624,551-556 (2023).

Https://doi.org/10.1038/s41586-023-06791-1

Welcome to subscribe "Shulou Technology Information " to get latest news, interesting things and hot topics in the IT industry, and controls the hottest and latest Internet news, technology news and IT industry trends.