Combining Newton interpolation and deep learning for image classification

Yongfeng Zhang, Changjing Shang

Research output: Contribution to journalArticlepeer-review

8 Citations (SciVal)
131 Downloads (Pure)

Abstract

A novel approach for image classification, by integrating deep learning and feature interpolation, supported with advanced learning classification techniques, is presented. The recently introduced deep spatiotemporal inference network (DeSTIN) is employed to carry out limited original feature extraction. Newton interpolation is then used to artificially increase the dimensionality of the extracted feature sets for accurate classification, without incurring heavy computational cost. Support vector machines are utilised for image classification. The proposed approach is tested against the popular MNIST dataset of handwritten digits, demonstrating the potential of the approach.
Original languageEnglish
Pages (from-to)40-42
JournalElectronics Letters
Volume51
Issue number1
DOIs
Publication statusPublished - Jan 2015

Keywords

  • learning (artificial intelligence)
  • interpolation
  • support vector machines
  • spatiotemporal phenomena
  • Newton method
  • feature extraction
  • image classification

Fingerprint

Dive into the research topics of 'Combining Newton interpolation and deep learning for image classification'. Together they form a unique fingerprint.

Cite this