This article proposes a new spike encoding and decoding algorithm for analog data. The algorithm uses the pulsewidth modulation principles to achieve a high reconstruction accuracy of the signal, along with a high level of data compression. Two benchmark data sets are used to illustrate the method: stock index time series and human voice data. Applications of the method for spiking neural network (SNN) modeling and neuromorphic implementations are discussed. The proposed method would allow the development of new applications of SNNs as regression techniques for predictive time-series modeling.
|Number of pages||12|
|Journal||IEEE Transactions on Neural Networks and Learning Systems|
|Early online date||14 Nov 2019|
|Publication status||Published - 6 Oct 2020|
Bibliographical noteFunding Information:
Manuscript received September 11, 2017; revised May 2, 2018, October 4, 2018, February 4, 2019, and August 30, 2019; accepted October 3, 2019. Date of publication November 14, 2019; date of current version October 6, 2020. This work was supported in part by UPV/EHU PPGA19/48. (Corresponding author: Ander Arriandiaga.) A. Arriandiaga and E. Portillo are with the Department of Automatic Control and Systems Engineering, Faculty of Engineering, University of the Basque Country, 48080 Bilbao, Spain (e-mail: email@example.com).
Dr. Portillo received a grant funded by the Basque Government and a prize for outstanding doctoral thesis in 2010.
© 2012 IEEE.
Copyright 2020 Elsevier B.V., All rights reserved.
- Analog data
- data compression
- spike encoding
- spike series decoding
- spiking neural networks (SNNs)
- streaming data