Researchers from DGIST have developed a new generation semiconductor artificial intelligence technology that imitates the work of a human of the brain.
A team led by Professor Kwon Hek-jun has created a neuromorphic device capable of storing multiple levels of data similar to neurons.
Traditional computing devices have disadvantages in speed and energy efficiency. In the search for a solution to this problem, researchers developed synaptic field-effect transistors using hafnium oxide and tin disulfide.
This made it possible to create a device that works 10 000 times faster than human synapses and consumes very little energy.
Professor Kwon noted that their research is an important step toward creating a next-generation computing architecture. He expressed confidence that this innovation will find application in various fields related to artificial intelligence and machine learning. p>
The study was published in the journal Advanced Science. It promises to make a significant contribution to the development of artificial intelligence technologies and neuromorphic systems.