Customer care
+34 913 67 09 92
Login
Follow us
next-generation-artifi

AI Semiconductor Mimics Brain Efficiency

Pioneering Semiconductors: A Brain-Inspired Future

A research team led by Prof. Kwon Hyuk-jun from the DGIST Department of Electrical Engineering and Computer Science has achieved a significant breakthrough in artificial intelligence (AI) semiconductor technology, crafting a solution that mirrors the efficiency of the human brain in AI and neuromorphic systems. This innovative technology is poised to overcome the challenges of energy efficiency and operational speed faced by traditional computational devices, heralding a new era for computing.

Overcoming Traditional Architecture Challenges

The advancement of AI has triggered an exponential growth in the demand for energy-efficient and fast-operating semiconductor technology. Traditional computing devices, grounded in von Neumann architecture, encounter challenges in speed and energy efficiency due to data processing bottlenecks. In this context, research into neuromorphic devices, which emulate the simultaneous computing and memory functions of biological neurons, has gained prominence.

A Revolutionary Neuromorphic Technology

Prof. Kwon’s team has developed synaptic field-effect transistors utilizing hafnium oxide, known for its robust electrical properties, and thin layers of tin disulfide, resulting in a three-terminal neuromorphic device capable of storing multiple data levels akin to neurons. This device not only replicates biological characteristics such as short- and long-term properties but also responds 10,000 times faster than human synapses and consumes minimal energy.

Prof. Hyuk-Jun Kwon stated, “This research marks a crucial step toward the next-generation computing architecture, which necessitates low power consumption and high-speed computation. We have developed high-performance neuromorphic hardware using two-dimensional channels and ferroelectric hafnium oxide, and the innovation is expected to find various AI and machine learning-related applications in the future.”

REQUEST FOR A QUOTE