Multivariate Time Series Classification Using Spiking Neural Networks

07/07/2020
by   Haowen Fang, et al.
0

There is an increasing demand to process streams of temporal data in energy-limited scenarios such as embedded devices, driven by the advancement and expansion of Internet of Things (IoT) and Cyber-Physical Systems (CPS). Spiking neural network has drawn attention as it enables low power consumption by encoding and processing information as sparse spike events, which can be exploited for event-driven computation. Recent works also show SNNs' capability to process spatial temporal information. Such advantages can be exploited by power-limited devices to process real-time sensor data. However, most existing SNN training algorithms focus on vision tasks and temporal credit assignment is not addressed. Furthermore, widely adopted rate encoding ignores temporal information, hence it's not suitable for representing time series. In this work, we present an encoding scheme to convert time series into sparse spatial temporal spike patterns. A training algorithm to classify spatial temporal patterns is also proposed. Proposed approach is evaluated on multiple time series datasets in the UCR repository and achieved performance comparable to deep neural networks.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/22/2021

Noise-Robust Deep Spiking Neural Networks with Temporal Information

Spiking neural networks (SNNs) have emerged as energy-efficient neural n...
research
02/19/2020

Exploiting Neuron and Synapse Filter Dynamics in Spatial Temporal Learning of Deep Spiking Neural Network

The recent discovered spatial-temporal information processing capability...
research
10/17/2021

Backpropagation with Biologically Plausible Spatio-Temporal Adjustment For Training Deep Spiking Neural Networks

The spiking neural network (SNN) mimics the information processing opera...
research
11/09/2021

Unsupervised Spiking Instance Segmentation on Event Data using STDP

Spiking Neural Networks (SNN) and the field of Neuromorphic Engineering ...
research
03/01/2019

Integrating Temporal Information to Spatial Information in a Neural Circuit

In this paper, we consider a network of spiking neurons with a determini...
research
10/19/2021

An Adaptive Sampling and Edge Detection Approach for Encoding Static Images for Spiking Neural Networks

Current state-of-the-art methods of image classification using convoluti...
research
06/21/2022

TCJA-SNN: Temporal-Channel Joint Attention for Spiking Neural Networks

Spiking Neural Networks (SNNs) is a practical approach toward more data-...

Please sign up or login with your details

Forgot password? Click here to reset