Kernel Application of the Stacked Crossbar Array Composed of Self‐Rectifying Resistive Switching Memory for Convolutional Neural Networks. (9th December 2019)

• Record Type: Journal Article
• Authors: Kim, Yumin; Kim, Jihun; Kim, Seung Soo; Kwon, Young Jae; Kim, Gil Seop; Jeon, Jeong Woo; Kwon, Dae Eun; Yoon, Jung Ho; Hwang, Cheol Seong
• Is Part Of: Advanced intelligent systems. Volume 2:Number 2(2020)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2019-12-09
• Subjects: convolutional neural networks -- hafnium oxide -- kernels -- self-rectifying resistive switching random access memory -- stacked crossbar arrays; Artificial intelligence -- Periodicals; Robotics -- Periodicals; Control theory -- Periodicals; 006.3
• DOI: 10.1002/aisy.201900116
• Languages: English
• ISSNs: 2640-4567

Abstract

Abstract : Herein, a feasible method is provided for circuit implementation of the convolutional neural network (CNN) in neuromorphic hardware using the multiple layers‐stacked resistance switching random access memory (ReRAM). The specific ReRAM is accompanied by self‐rectification functionality. The single‐input multiple‐output (SIMO) scheme is an optimum method in the extraction of the features of a letter with a versatile selection of the intended features, whereas the multiple‐input single‐output (MISO) scheme provides a highly efficient method to extract the features from the color image, which is composed of several component color images. The Pt/HfO2− x /TiN‐based self‐rectification ReRAM that is integrated into the sidewalls of the two‐layer structure provides a sound framework for the circuit implementation of the SIMO and MISO schemes. The appropriate selection of the kernels for image compression and feature extraction greatly facilitates the CNN in neuromorphic hardware. Abstract : A new method for convolutional kernel operation using stacked crossbar array with variation‐prone self‐rectifying resistance switching random access memory (ReRAM) is proposed. This method is realized by a current mirror–based circuit and the novel method of ReRAM state mapping which enable the multichannel input image which is processed at once.