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

Falez Pierre; Tirilly Pierre; Bilasco Loan Marius; Devienne Philippe; Boulet Pierre

首页> 外文期刊>Pattern Recognition: The Journal of the Pattern Recognition Society >Unsupervised visual feature learning with spike-timing-dependent plasticity: How far are we from traditional feature learning approaches?

【24h】

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

机译：无监督的视觉特征学习，绰号依赖塑性功能：我们来自传统特色学习方法有多远？

获取原文

获取原文并翻译 | 示例

掌桥外文数据库（机构版） >>

开具论文收录证明 >>

文献代查 >>

页面导航

摘要
著录项
相似文献
相关主题

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.

机译：配备延迟编码和尖峰定时依赖性塑性规则的尖峰神经网络（SNNS）提供了解决标准计算机视觉方法的数据和能量瓶颈的替代方案：它们可以在没有监控的情况下学习视觉功能，可以通过超低功耗硬件实现建筑。但是，它们在图像分类中的性能从未评估了最近的图像分类。在本文中，我们将SNNS比较三个可视识别数据集上的自动编码器，并将SNN的使用扩展到彩色图像。结果分析有助于我们识别SNNS的一些瓶颈：中心/偏离中心编码的限制，特别是对于彩色图像，以及目前抑制机制的无效性。应解决这些问题以构建有效的SNN进行图像识别。（c）2019年elestvier有限公司保留所有权利。

著录项

来源
《Pattern Recognition: The Journal of the Pattern Recognition Society》 |2019年第2019期|共12页
作者
Falez Pierre; Tirilly Pierre; Bilasco Loan Marius; Devienne Philippe; Boulet Pierre;
展开▼
作者单位

Univ Lille CRIStAL Ctr Rech Informat Signal &

Automat Lille Cent Lille CNRS UMR 9189 F-59000 Lille France;

Univ Lille CRIStAL Ctr Rech Informat Signal &

Automat Lille Cent Lille IMT Lille Douai CNRS UMR 9189 F-59000 Lille France;

Univ Lille CRIStAL Ctr Rech Informat Signal &

Automat Lille Cent Lille CNRS UMR 9189 F-59000 Lille France;

Univ Lille CRIStAL Ctr Rech Informat Signal &

Automat Lille Cent Lille CNRS UMR 9189 F-59000 Lille France;

Univ Lille CRIStAL Ctr Rech Informat Signal &

Automat Lille Cent Lille CNRS UMR 9189 F-59000 Lille France;

展开▼
收录信息
原文格式 PDF
正文语种 eng
中图分类计算技术、计算机技术;
关键词
Feature learning; Unsupervised learning; Spiking neural networks; Spike-timing dependent plasticity; Auto-encoders; Image recognition;

机译：特色学习;无人监督学习;尖峰神经网络;尖峰定时依赖塑性;自动编码器;图像识别;

相似文献

外文文献
中文文献
专利

1. Unsupervised visual feature learning with spike-timing-dependent plasticity: How far are we from traditional feature learning approaches? [J] . Falez Pierre, Tirilly Pierre, Bilasco Loan Marius, Pattern Recognition: The Journal of the Pattern Recognition Society . 2019,第期

机译：无监督的视觉特征学习，绰号依赖塑性功能：我们来自传统特色学习方法有多远？
2. Effects of bursting dynamic features on the generation of multi-clustered structure of neural network with symmetric spike-timing-dependent plasticity learning rule [J] . Liu Hui, Song Yongduan, Xue Fangzheng, Chaos . 2015,第10a12期

机译：突发性动态特征对对称时脉相关可塑性学习规则的神经网络多聚类结构生成的影响
3. Learning representation hierarchies by sharing visual features: a computational investigation of Persian character recognition with unsupervised deep learning [J] . Sadeghi Zahra, Testolin Alberto Cognitive processing . 2017,第3期

机译：通过分享视觉特征学习代表层次结构：与无监督深度学习的波斯字符识别的计算调查
4. Unsupervised features extraction from asynchronous silicon retina through Spike-Timing-Dependent Plasticity [C] . Bichler Olivier, Querlioz Damien, Thorpe Simon J., The 2011 International Joint Conference on Neural Networks . 2011

机译：通过峰值计时相关的可塑性从异步硅视网膜中提取无监督特征
5. Learning Features for Unsupervised Learning and Reinforcement Learning [D] . Song, Zhao. 2018

机译：无监督学习和强化学习的学习功能
6. Unsupervised Learning of Visual Features through Spike Timing Dependent Plasticity [O] . Timothée Masquelier, Simon J Thorpe 2007

机译：通过峰值时序相关可塑性进行无监督的视觉特征学习
7. Unsupervised Learning of Visual Features through Spike Timing Dependent Plasticity [O] . Timothée Masquelier, Simon J. Thorpe 2010

机译：通过峰值时序相关可塑性进行无监督的视觉特征学习

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

摘要

著录项

相似文献

相关主题

期刊订阅