포항공과대학교 · Engineering
하이운산 황 교수의 연구실은 신경형 컴퓨팅을 구현하기 위한 나노스케일 전자 소자 기반의 뉴모르픽 시스템 개발에 중점을 두고 있습니다. 주로 RRAM(저항성 스위칭 메모리) 기반의 학습 가능한 시냅스 소자와 타입 전환 특성을 활용한 스파iking 뉴런 소자 개발을 통해 초소형·저전력 뉴럴 네트워크 하드웨어를 연구하고 있습니다. 특히, 산화질소 가스를 이용한 고질적 산화질화막 제조 기술을 통해 소자 신뢰성과 전기적 특성을 극대화하는 데도 기여하고 있습니다.
표시된 성과는 수집된 데이터 기준으로 산출되며, 일부 차이가 있을 수 있습니다.
Hardware artificial neural network (ANN) systems with high density synapse array devices can perform massive parallel computing for pattern recognition with low power consumption. To implement a neuromorphic system with on-chip training capability, we need to develop an ideal synapse device with various device requirements, such as scalability, MLC characteristics, low power operation, data retention, and symmetric/linear conductance changes under potentiation/depression modes. Although various
This letter presents a unique process to grow high quality ultrathin (∼60 Å) gate dielectrics using N2O (nitrous oxide) gas. Compared with conventional rapid thermally grown oxide in the O2, the new oxynitride dielectrics show very large charge-to-breakdown (at +50 mA/cm2, 850 C/cm2 for oxynitride compared to 95 C/cm2 for the control thermal oxide) and less charge trapping under constant current stress. Significantly reduced interface state generation was also observed under constant current str
Abstract This study demonstrates an integrate and fire (I&F) neuron using threshold switching (TS) devices to implement spike‐based neuromorphic system. An I&F neuron can be realized using the hysteric voltage switch characteristics of a TS device. To investigate the effects of various TS devices on neuron behavior, neurons are compared using three different types of TS device: NbO 2 ‐based insulator‐to‐metal transition (IMT) device, B–Te‐based ovonic threshold switching device, and Ag/H
Efforts to develop scalable learning algorithms for implementation of networks of spiking neurons in silicon have been hindered by the considerable footprints of learning circuits, which grow as the number of synapses increases. Recent developments in nanotechnologies provide an extremely compact device with low-power consumption.In particular, nanoscale resistive switching devices (resistive random-access memory (RRAM)) are regarded as a promising solution for implementation of biological synap
The electrical and physical characteristics of oxynitride grown in N/sub 2/O gas ambient have been studied. The dielectric growth rate in N/sub 2/O was found to be highly controllable and lower than that in O/sub 2/. Auger electron spectroscopy studies of oxynitride show a nitrogen-rich layer near the Si-SiO/sub 2/ interface. Compared with the control oxide, the oxynitride shows excellent electrical characteristics such as excellent diffusion barrier to dopant (BF/sub 2/), a significant reductio
Creation of nanometer-scale conductive filaments in resistive switching devices makes them appealing for advanced electrical applications. While in situ electrical probing transmission electron microscopy promotes fundamental investigations of how the conductive filament comes into existence, it does not provide proof-of-principle observations for the filament growth. Here, using advanced microscopy techniques, electrical, 3D compositional, and structural information of the switching-induced con
