Abstract

Resistive switching random-access memory (ReRAM) is a two-terminal device based on ion migration to induce resistance switching between a high resistance state (HRS) and a low resistance state (LRS). ReRAM is considered one of the most promising technologies for artificial synapses in brain-inspired neuromorphic computing systems. However, there is still a lack of general understanding about how to develop such a gestalt system to imitate and compete with the brain's functionality and efficiency. Spiking neural networks (SNNs) are well suited to describe the complex spatiotemporal processing inside the brain, where the energy efficiency of computation mostly relies on the spike carrying information about both space (which neuron fires) and time (when a neuron fires). This work addresses the methodology and implementation of a neuromorphic SNN system to compute the temporal information among neural spikes using ReRAM synapses capable of spike-timing dependent plasticity (STDP). The learning and recognition of spatiotemporal spike sequences are experimentally demonstrated. Our simulation study shows that it is possible to construct a multi-layer spatiotemporal computing network. Spatiotemporal computing also enables learning and detection of the trace of moving objects and mimicking of the hierarchy structure of the biological visual cortex adopting temporal-coding for fast recognition.

Highlights

  • The most relevant advances of arti cial intelligence (AI) are currently in the area of deep neural networks (DNNs),[1] which enable the learning and recognition of images, sounds, and speech

  • A pre-synaptic neuron (PRE) is connected to a post-synaptic neuron (POST) via a synapse between the PRE axon and the POST dendrite

  • With a high positive voltage applied on the top electrode (VTE) of the Resistive switching random-access memory (ReRAM) device, the device can switch from a high resistance state (HRS) to low resistance state (LRS), called set transition

Read more

Summary

Introduction

Paper processing unit (GPU) utilizing the complementary metal-oxide-semiconductor (CMOS) technology, the slowing down of Moore’s law may create a critical issue for the future progress of DNNs. Learning usually takes place via spike-timing dependent plasticity (STDP),[23,24,25,26,27] where synapses can update their weight according to the timing between spikes of the pre-synaptic neuron (PRE) and post-synaptic neuron (POST). This approach provides a more biologically plausible way to implement neuromorphic computing. Paper feasibility of ReRAM synapses for the implementation of a brain-like neuromorphic system with efficient spatiotemporal coding

ReRAM device as an arti cial synapse
Computation of the temporal correlation of spikes
Learning of the temporal correlation
Learning and recognition of the spike sequence
Learning of a spiking sequence
Detection of a moving object
Spatiotemporal network for pattern recognition
ReRAM synapse
CMOS neuron
Training and test control system
Conclusions
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