A research institute specializing in Materials Science

Press release

R&D | KIMS developed the world’s first neuromorphic semiconductor device with high-density, high-reliability by making thin film of lithium-ion battery materials

Page info

Date23-02-15 19:08 Hit402

Contents

KIMS developed the world’s first neuromorphic semiconductor device with high-density, high-reliability by making thin film of lithium-ion battery materials

The world's highest level of handwriting pattern recognition rate!


A research team led by Dr. Yong-hun Kim and Dr. Jeong-Dae Kwon has successfully developed the world’s first neuromorphic semiconductor device with high-density and high reliability by developing a thin film of lithium-ion battery materials. This is a key element manufacturing technology for the next-generation artificial intelligence semiconductor with high density and high reliability by producing ultra-thin lithium ion, a key material of lithium-ion batteries that have been in the spotlight recently, and combining it with two-dimensional nano-materials. The research team is in the Surface & Nano Materials Division at the Korea Institute of Materials Science (KIMS), a government-funded research institute under the Ministry of Science and ICT.



A neuromorphic semiconductor device has synapses and neurons similar to the human brain, which requires to development of a synaptic device that is responsible for processing and memorizing the information. The synaptic device receives signals from neurons and modulates the synaptic weight (connection strength) in various ways to simultaneously process and store information. In particular, satisfying the linearity and symmetry of synaptic weights can easily make realize various pattern recognition with low power.



Traditional methods for controlling synaptic weights have been to use charge traps between interfaces of heterogeneous materials or oxygen ions. In this case, however, it is difficult to control the movement of ions in the desired direction according to the external electric field. The researchers solved this problem with an artificial intelligence semiconductor device with high density by developing a thin film process while maintaining the mobility of lithium ions according to the external electric field. By developing a thin film with a thickness of several tens of nanometers, it is suitable for the existing semiconductor process as it enables fine pattern processing while controlling the thickness of the wafer scale.



The research team succeeded in developing a thin film of lithium-ion using the vacuum sputtering deposition method which is used in general semiconductor processes. The thickness of the deposited film is less than 100 nanometers. After a transistor-type device on a silicon wafer substrate is manufactured through a semiconductor process, and when an electric field is applied from the outside, the lithium ions in the charged lithium thin film reversibly move so that the conductivity of the channel can be precisely controlled. The research team implemented an artificial neural network learning pattern using this synapse device and developed handwriting image pattern recognition. The artificial intelligence semiconductor device shows a handwriting pattern recognition rate of about 96.77% by maintaining the characteristics of finely adjusted synaptic weight even in an electric field repeated more than 500 times.



The research team mentioned that “Our next-generation neuromorphic semiconductor device does not require CPU and memory, the traditional Von Neumann-type information processing device and information storage device. It can simultaneously process and stores information and learns and recognizes images such as handwriting patterns. It is expected to be applied to various low-power artificial intelligence devices such as world-class neuromorphic hardware systems, haptic devices, and vision sensors.”



The research was carried out through the major projects of KIMS and the material innovation leading project of the National Research Foundation of Korea Materials Innovation Leading Project with the support of the Ministry of Science and ICT. The outcomes of the research were published in ACS AMI (ACS Applied Materials & Interfaces, IF: 10.383), a world-renowned academic journal on November 17, 2022. (First author: Byeong-jin Park, student researcher, co-corresponding author: Prof. Je-in Lee, Pusan National University)



The research team is conducting follow-up research on intelligent wearable devices by applying them to low-power artificial intelligence devices and wearable edging devices.



KIMS developed the world’s first neuromorphic semiconductor device with high-density, high-reliability by making thin film of lithium-ion battery materials