Kernel Application of the Stacked Crossbar Array Composed of Self‐Rectifying Resistive Switching Memory for Convolutional Neural Networks

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.

Area-Type Electronic Bipolar Switching Al/TiO1.7/TiO2/Al Memory with Linear Potentiation and Depression Characteristics

“…These devices have been recently found suitable for synaptic weight storage in the neural network structure, especially in neuromorphic hardware. − In this case, information processing through the neural and neuromorphic networks involves a large number of vector-matrix multiplication (VMM) steps, where the vector usually refers to the input of the information and the output of the neurons, and the matrix represents the synaptic weights that connect the neurons. With its passive cross-bar array (CBA) configuration, the linear VMM operation could be efficiently performed in a hardware platform for both artificial neural networks (ANNs) and the more biologically plausible spiking neural networks (SNNs).…”

Memristive Crossbar Arrays for Storage and Computing Applications

“…The large work function difference between the top and bottom electrodes is essential for the asymmetric effective barrier seen in the top and bottom electrodes to enable the rectifying feature. So far, the self‐rectifying memory devices with such bilayer device structures have been intensively studied, for example, NiSi/HfO x /TiN, [ 180 ] Ge/HfO x /Ni, [ 181 ] He‐LiNbO 3 /Pt/SiO 2 /LiNbO 3 , [ 182 ] Pt/Ta 2 O 5 /HfO 2− x /TiN, [ 183 ] Ni/HfO 2 /SiO 2 /Si diode, [ 184 ] Pt/TaO x /n‐Si, [ 185 ] Al/MoO x /Pt, [ 186 ] (ITO)/InGaZnO/ITO, [ 187 ] Pt/HfO 2− x /TiN, [ 188 ] Pt/amorphous In−Ga−Zn−O (a‐IGZO)/TaO x /Al 2 O 3 /W, [ 189 ] Ti/SiO x N y /AIN/Pt, [ 190 ] Pd/HfO 2 /WO x /W, [ 191 ] Ag/a‐Si/p + ‐Si, [ 192 ] Au/ZrO 2 :nc‐Au/n + Si, [ 193 ] Au/Li−ZnO/ZnO/Pt, [ 194 ] Ni/SiN/HfO 2 /Si, [ 195 ] Pd/HfO 2 /TaO x /Ta, [ 196 ] Ni/Al 2 O 3 /p‐Al doped GaN (p‐AlGaN), [ 197 ] Si 3 N 4 /SiO 2 /Si, [ 198 ] Pt/Ta 2 O 5 /HfO 2− x /Hf, [ 199 ] Ti/GaO x /NbO x /Pt, [ 200 ] Ti/NiO x /Al 2 O 3 /Pt, [ 201 ] etc. Li et al reported a p‐Si/SiO 2 /n‐Si memristor.…”

Hardware Implementation of Neuromorphic Computing Using Large‐Scale Memristor Crossbar Arrays

“…There are a few reports on fabricating less‐layered 3D vertical CBAs, [ 159,161,167 ] and the implementation of CNN with vertical two‐layer Pt/HfO 2‐ x /TiN random access memory (ReRAM or RRAM) CBA has been reported very recently. [ 166 ] However, the 3D vertical CBA technology is still insufficient and further efforts to address these challenges are needed.…”