Temporal Pattern Coding in Deep Spiking Neural Networks
METADATA ONLY
Loading...
Author / Producer
Date
2021
Publication Type
Conference Paper
ETH Bibliography
yes
Citations
Altmetric
METADATA ONLY
Data
Rights / License
Abstract
Deep Artificial Neural Networks (ANNs) employ a simplified analog neuron model that mimics the rate transfer function of integrate-and-fire neurons. In Spiking Neural Networks (SNNs), the predominant information transmission method is based on rate codes. This code is inefficient from a hardware perspective because the number of transmitted spikes is proportional to the encoded analog value. Alternate codes such as temporal codes that are based on single spikes are difficult to scale up for large networks due to their sensitivity to spike timing noise. Here we present a study of an encoding scheme based on temporal spike patterns. This scheme inherits the efficiency of temporal codes but retains the robustness of rate codes. The pattern code is evaluated on MNIST, CIFAR-10, and ImageNet image classification tasks. We compare the network performance of ANNs, rate-coded SNNs, and temporal-coded SNNs, using the classification error and operation count as performance metrics. We also estimate the power consumption of the digital logic needed for the operations associated with each encoding type, and the impact of the bit precision of the weights and activations. On ImageNet, the temporal pattern code achieves up to 35times reduction in the estimated power consumption compared to the rate-coded SNN, and 42times compared to the ANN. The classification error of the pattern-coded SNN is increased by < 1% compared to the ANN, and decreased by 2% compared to the rate-coded SNN.
Permanent link
Publication status
published
Editor
Book title
2021 International Joint Conference on Neural Networks (IJCNN)
Journal / series
Volume
Pages / Article No.
9533837
Publisher
IEEE
Event
2021 International Joint Conference on Neural Networks (IJCNN 2021)
Edition / version
Methods
Software
Geographic location
Date collected
Date created
Subject
Organisational unit
02533 - Institut für Neuroinformatik / Institute of Neuroinformatics