Unsupervised visual feature learning with spike-timing-dependent plasticity: How far are we from traditional feature learning approaches?

PATTERN RECOGNITION

卷:93

Article

Falez, Pierre¹  Tirilly, Pierre²  Bilasco, Loan Marius¹  Devienne, Philippe¹  Boulet, Pierre¹ 

[1] Univ Lille, CRIStAL Ctr Rech Informat Signal & Automat Lille, Cent Lille, CNRS,UMR 9189, F-59000 Lille, France

[2] Univ Lille, CRIStAL Ctr Rech Informat Signal & Automat Lille, Cent Lille, IMT Lille Douai,CNRS,UMR 9189, F-59000 Lille, France

关键词: Feature learning;    Unsupervised learning;    Spiking neural networks;    Spike-timing dependent plasticity;    Auto-encoders;    Image recognition;   

DOI  :  10.1016/j.patcog.2019.04.016

来源: Elsevier

【 摘 要 】

Spiking neural networks (SNNs) equipped with latency coding and spike-timing dependent plasticity rules offer an alternative to solve the data and energy bottlenecks of standard computer vision approaches: they can learn visual features without supervision and can be implemented by ultra-low power hardware architectures. However, their performance in image classification has never been evaluated on recent image datasets. In this paper, we compare SNNs to auto-encoders on three visual recognition datasets, and extend the use of SNNs to color images. The analysis of the results helps us identify some bottlenecks of SNNs: the limits of on-center/off-center coding, especially for color images, and the ineffectiveness of current inhibition mechanisms. These issues should be addressed to build effective SNNs for image recognition. (C) 2019 Elsevier Ltd. All rights reserved.

【 授权许可】

Free