Investigation of Deep Spiking Neural Networks Utilizing Gated Schottky Diode as Synaptic Devices

Deep learning produces a remarkable performance in various applications such as image classification and speech recognition. However, state-of-the-art deep neural networks require a large number of weights and enormous computation power, which results in a bottleneck of efficiency for edge-device ap...

Full description

Saved in:
Bibliographic Details
Published in:Micromachines (Basel) 2022-10, Vol.13 (11), p.1800
Main Authors: Lee, Sung-Tae, Bae, Jong-Ho
Format: Article
Language:English
Subjects:
Accuracy
Artificial neural networks
Data integrity
Deep learning
Energy conservation
Hardware
hardware-based neural networks
Image classification
in-memory computing
Investigations
Machine learning
Methods
Neural networks
neuromorphic device
Neurons
Object recognition
off-chip learning
Power consumption
Power management
Schottky diodes
Software
Speech recognition
Spiking
spiking neural networks
Technology application
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Deep learning produces a remarkable performance in various applications such as image classification and speech recognition. However, state-of-the-art deep neural networks require a large number of weights and enormous computation power, which results in a bottleneck of efficiency for edge-device applications. To resolve these problems, deep spiking neural networks (DSNNs) have been proposed, given the specialized synapse and neuron hardware. In this work, the hardware neuromorphic system of DSNNs with gated Schottky diodes was investigated. Gated Schottky diodes have a near-linear conductance response, which can easily implement quantized weights in synaptic devices. Based on modeling of synaptic devices, two-layer fully connected neural networks are trained by off-chip learning. The adaptation of a neuron’s threshold is proposed to reduce the accuracy degradation caused by the conversion from analog neural networks (ANNs) to event-driven DSNNs. Using left-justified rate coding as an input encoding method enables low-latency classification. The effect of device variation and noisy images to the classification accuracy is investigated. The time-to-first-spike (TTFS) scheme can significantly reduce power consumption by reducing the number of firing spikes compared to a max-firing scheme.
ISSN:2072-666X
2072-666X
DOI:10.3390/mi13111800