Artificial intelligence (AI) will enable machines to think and solve complex tasks like human beings. In recent years, artificial neural networks have improved recognition and classification accuracy. However, state-of-the-art deep learning algorithms require large network models with multiple layers, which pose significant challenges for complementary metal-oxide-semiconductor (CMOS) implementation due to limitations in conjoining computation, memory, and communication requirements in large networks. As an alternative hardware platform, resistive devices (memristor) have been proposed for weight storage and fast parallel neural computing with low power consumption. The paralleism property of the resistive corssbar arrays for matrix-vector multiplication enables significant acceleration of core neural computations. In this talk, Dr. Choi will present a systematic study on the fundamental understanding of resistive switching devices. He will also introduce the appliation of memristor crossbar network in neuromorphic computing through dataclustering based on unsupervised learning, which suggests potential applications of memristor network for effective data classification for solving real-world problems. In addition, he will introduce epitaxial RAM or epiRAM, a recently developed resistive switching devices, which possesses all the required characteristics for neuromorphic computing. The epiRAM, single-crystalline-based memristive devices, show precise weight controls with a superior online learning accuracy of 95.1% – a key step paving the way towards post von Neumann computing. Finally, he will discuss the projections and future direction of the memristor-based neuromorphic computing system.
Dr. Shinhyun Choi is a Postdoctoral Associate at Massachusetts Institute of Technology (MIT). His research at MIT focuses on (1) neuromorphic computing devices using resistive switching elements; and (2) its application in integrated neuromorphic network. He graduated Summa Cum Laude from Seoul National University; Korea in 2009 with a Bachelor of Science in Electrical Engineering. He obtained his Master’s and Ph.D. in Electrical Engineering at the University of Michigan, Ann Arbor in 2011 and 2015, respectively. During his graduate studies, he investigated the fundamental understanding and neuromorphic applications of resistive switching devices. He is the author/co-author of 14 peer-reviewed articles including Nature, Nature Materials, Nature Communiations, Nano Letters, ACS Nano. His works have been selected as front covers in Nature, highlighted in Nature News & Views, Nature Materials News & Views, Nature Nanotechnology Research Highlights, and featured as cover pages on MIT news. His works have also been covered on numerous media outlets including EE times, IEEE Spectrum, EE NEWs and the Verge. He was a recipient of Jeongsong Scholarship (2009 – 2011) and Samsung Scholarship (2011- 2015).