Logic Computing with Stateful Neural Networks of Resistive Switches. Issue 38 (5th August 2018)

• Record Type: Journal Article
• Authors: Sun, Zhong; Ambrosi, Elia; Bricalli, Alessandro; Ielmini, Daniele
• Is Part Of: Advanced materials. Volume 30:Issue 38(2018)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2018-08-05
• Subjects: in‐memory computing -- neural networks -- neuromorphic -- resistive switching memory -- stateful logic; Materials -- Periodicals; Chemical vapor deposition -- Periodicals; 620.11
• DOI: 10.1002/adma.201802554
• Languages: English
• ISSNs: 0935-9648

Abstract

Abstract: Brain‐inspired neural networks can process information with high efficiency, thus providing a powerful tool for pattern recognition and other artificial intelligent tasks. By adopting binary inputs/outputs, neural networks can be used to perform Boolean logic operations, thus potentially surpassing complementary metal–oxide–semiconductor logic in terms of area efficiency, execution time, and computing parallelism. Here, the concept of stateful neural networks consisting of resistive switches, which can perform all logic functions with the same network topology, is introduced. The neural network relies on physical computing according to Ohm's law, Kirchhoff 's law, and the ionic migration within an output switch serving as the highly nonlinear activation function. The input and output are nonvolatile resistance states of the devices, thus enabling stateful and cascadable logic operations. Applied voltages provide the synaptic weights, which enable the convenient reconfiguration of the same circuit to serve various logic functions. The neural network can solve all two‐input logic operations with just one step, except for the exclusive‐OR (XOR) needing two sequential steps. 1‐bit full adder operation is shown to take place with just two steps and five resistive switches, thus highlighting the high efficiencies of space, time, and energy of logic computing with the stateful neural network. Abstract : The concept of a stateful neural network is introduced based on a resistive memory circuit. Thanks to the universality and flexibility of the neural network, the circuit enables one‐step operation for all linearly separable logic functions, thus extremely reducing the numbers of computing steps and devices for stateful logic computing, for instance, two steps and five devices for the 1‐bit full adder.