Improved graph-based SFA: information preservation complements the slowness principle

Author:

Escalante-B. Alberto N.ORCID,Wiskott LaurenzORCID

Abstract

AbstractSlow feature analysis (SFA) is an unsupervised learning algorithm that extracts slowly varying features from a multi-dimensional time series. SFA has been extended to supervised learning (classification and regression) by an algorithm called graph-based SFA (GSFA). GSFA relies on a particular graph structure to extract features that preserve label similarities. Processing of high dimensional input data (e.g., images) is feasible via hierarchical GSFA (HGSFA), resulting in a multi-layer neural network. Although HGSFA has useful properties, in this work we identify a shortcoming, namely, that HGSFA networks prematurely discard quickly varying but useful features before they reach higher layers, resulting in suboptimal global slowness and an under-exploited feature space. To counteract this shortcoming, which we call unnecessary information loss, we propose an extension called hierarchical information-preserving GSFA (HiGSFA), where some features fulfill a slowness objective and other features fulfill an information preservation objective. The efficacy of the extension is verified in three experiments: (1) an unsupervised setup where the input data is the visual stimuli of a simulated rat, (2) the localization of faces in image patches, and (3) the estimation of human age from facial photographs of the MORPH-II database. Both HiGSFA and HGSFA can learn multiple labels and offer a rich feature space, feed-forward training, and linear complexity in the number of samples and dimensions. However, the proposed algorithm, HiGSFA, outperforms HGSFA in terms of feature slowness, estimation accuracy, and input reconstruction, giving rise to a promising hierarchical supervised-learning approach. Moreover, for age estimation, HiGSFA achieves a mean absolute error of 3.41 years, which is a competitive performance for this challenging problem.

Publisher

Springer Science and Business Media LLC

Subject

Artificial Intelligence,Software

Reference56 articles.

1. Berkes, P. (2005a). Handwritten digit recognition with nonlinear Fisher discriminant analysis. In ICANN, LNCS (Vol. 3697, pp. 285–287). Berlin: Springer.

2. Berkes, P. (2005b). Pattern recognition with Slow Feature Analysis. Cognitive Sciences EPrint Archive (CogPrints). Retrieved February 24, 2012 from http://cogprints.org/4104/.

3. Berkes, P., & Wiskott, L. (2005). Slow Feature Analysis yields a rich repertoire of complex cell properties. Journal of Vision, 5(6), 579–602.

4. Blaschke, T., Zito, T., & Wiskott, L. (2007). Independent Slow Feature Analysis and nonlinear blind source separation. Neural Computation, 19(4), 994–1021.

5. Cootes, T. (2004). Face and gesture recognition research network (FG-NET) aging database. Retrieved June 17, 2009 from http://www-prima.inrialpes.fr/FGnet/.

Cited by 6 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. Exploring the Effects of Head-Mounted Augmented Reality on Helping Behaviour;Proceedings of the 22nd International Conference on Mobile and Ubiquitous Multimedia;2023-12-03

2. Improving image classification of one-dimensional convolutional neural networks using Hilbert space-filling curves;Applied Intelligence;2023-08-28

3. Consent in the Age of AR: Investigating The Comfort With Displaying Personal Information in Augmented Reality;CHI Conference on Human Factors in Computing Systems;2022-04-29

4. Slow Down to Go Better: A Survey on Slow Feature Analysis;IEEE Transactions on Neural Networks and Learning Systems;2022

5. Age of smile: a cross-cultural replication report of Ganel and Goodale (2018);Journal of Cultural Cognitive Science;2021-01-10

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3