New AI Transistor Mimics Human Brain at Room Temperature, Processing and Storing Information Simultaneously

Gamingdeputy reported on December 23 that scientists have made another major breakthrough in the field of AI.An AI synaptic transistor that mimics the human brain has recently been released.

This AI synaptic transistor operates similarly to human cognition, capable of processing and storing information simultaneously, marking a significant shift from traditional machine learning tasks to performing associative learning.

Source: Xiaodong Yan/Northwestern University

More importantly, this AI synaptic transistor canRoom temperature environmentEffective operation underIt has the advantages of fast operation, low energy consumption, and the ability to retain information even without power supply, and has broad application prospects.

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

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

In a digital computer, data needs to be moved back and forth between the microprocessor and memory, inevitably consuming a lot of energy and creating bottlenecks when trying to perform multiple tasks simultaneously.

In the human brain, memory and information processing are co-located and fully integrated, resulting in orders of magnitude higher energy efficiency. Our synaptic transistors also enable concurrent memory and information processing, more faithfully mimicking the brain.

Hersam's team developed synaptic transistors mainly using moiré patterns.

Gamingdeputy Note: Moire pattern is a geometric pattern that appears when two patterns are superimposed on each other. When two-dimensional materials are stacked, new properties emerge that are not present in a single-layer structure. When these hierarchical structures are twisted to form moiré patterns, it is possible to harvest unprecedented electronic properties.

In this new synaptic transistor, the researchers combined two different types of atomically thin materials, bilayer graphene and hexagonal boron nitride. Graphene and hexagonal boron nitride are structurally very similar, but they are also different enough to produce an unusually strong moiré effect, which allows manipulation of the electronic properties of the graphene layer.

This manipulation can be performed at room temperature, producing synaptic transistors with enhanced neuromorphic functions.

In an associative learning test, the AI ​​transistor can compare “101” and “111” and identify the latter as more similar to “000”.

This ability to handle complex and imperfect inputs has significant implications for real-world AI applications.

Gamingdeputy attaches the reference address of the paper