Empirical evaluation of whitening and optimization of feature learning

Nouman Qadeer, Xiabi Liu

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

2 Citations (Scopus)

Abstract

Deep learning and Feature learning emerged new field in machine learning and beat many, state of the arts results in diverse areas. Well established feature learning Sparse- Autoencoder was chosen in our work and tunes their different critical parameters. We have shown that tweaking right parameter can improved results and good features can be obtained. Different Whitening preprocessing techniques and optimization methods were applied on well known data set corel-100 and found out that Cost effective PCA whitening is also same reliable as cost prone other whitening techniques. Different Optimization methods were analyzed and experiments show L-BFGS beat CG as data goes large.

Original languageEnglish
Title of host publicationProceedings - UKSim-AMSS 16th International Conference on Computer Modelling and Simulation, UKSim 2014
EditorsJasmy Yunus, Richard Cant, Ismail Saad, David Al-Dabass, Zuwairie Ibrahim, Alessandra Orsoni
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages36-39
Number of pages4
ISBN (Electronic)9781479949236
DOIs
Publication statusPublished - 2014
Event16th UKSim-AMSS International Conference on Computer Modelling and Simulation, UKSim 2014 - Cambridge, United Kingdom
Duration: 26 Mar 201428 Mar 2014

Publication series

NameProceedings - UKSim-AMSS 16th International Conference on Computer Modelling and Simulation, UKSim 2014

Conference

Conference16th UKSim-AMSS International Conference on Computer Modelling and Simulation, UKSim 2014
Country/TerritoryUnited Kingdom
CityCambridge
Period26/03/1428/03/14

Keywords

  • Feature learning
  • Optimization
  • Sparseautoencoder
  • Whitening

Fingerprint

Dive into the research topics of 'Empirical evaluation of whitening and optimization of feature learning'. Together they form a unique fingerprint.

Cite this