Abstract

Resistive random-access memories are promising analog synaptic devices for efficient bio-inspired neuromorphic computing arrays. Here we first describe working principles for phase-change random-access memory, oxide random-access memory, and conductive-bridging random-access memory for artificial synapses. These devices could allow for dense and efficient storage of analog synapse connections between CMOS neuron circuits. We also discuss challenges and opportunities for analog synaptic devices toward the goal of realizing passive neuromorphic computing arrays. Finally, we focus on reducing spatial and temporal variations, which is critical to experimentally realize powerful and efficient neuromorphic computing systems.

Highlights

  • Artificial intelligence (AI) has allowed for significant technological advancements in image classification,[1,2,3] speech recognition,[4,5,6] strategic gaming,[7] and decision-making.[8,9,10,11,12] artificial neural networks (ANNs) require large amounts of computing power, especially for deep learning.[13]

  • Compared to Graphics Processing Units (GPUs), application-specific integrated circuit (ASIC) accelerators[17,18,19,20,21,22,23] and field-programmable gate array (FPGA) accelerators[24,25,26,27] demonstrated computing efficiency improvements. The performance of these complementary metal-oxide semiconductor (CMOS) based systems is limited by the large footprint of synaptic cells and frequent access to external memory.[28]

  • We evaluate potentiation threshold voltage variations determined from current-voltage measurements

Read more

Summary

INTRODUCTION

Artificial intelligence (AI) has allowed for significant technological advancements in image classification,[1,2,3] speech recognition,[4,5,6] strategic gaming,[7] and decision-making.[8,9,10,11,12] artificial neural networks (ANNs) require large amounts of computing power, especially for deep learning.[13]. Research has focused on experimentally demonstrating biologically observed phenomena, such as spike-timing-dependent plasticity (STDP), with artificial synapses.[42,43,44] how to efficiently utilize local updating rules with spikes remains an important question to tackle.[45] By contrast, bio-inspired neuromorphic computing focuses on implementing artificial neural network hardware built for learning algorithms that are well-defined mathematically. Material a-Si SiO2 ZrOx/HfOx NiO HfOx ZrO2 CuC GST TiO2 ZnO TiO2 ZrO2 SiOx TiOx ZnO w/Ti SiGe

STRATEGIES TO MINIMIZE VARIATIONS
Scaling
Structure modification
Embedding nanoparticles
Defining channels in single crystals
Findings
CONCLUDING REMARKS
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call