Adaptive, optical, radial basis function neural network for handwritten digit recognition

Wesley E. Foor, Mark A. Neifeld

Research output: Contribution to journalArticlepeer-review

5 Scopus citations


An adaptive, optical, radial basis function classifier for handwritten digit recognition is experimentally demonstrated. We describe a spatially multiplexed system that incorporates an on-line adaptation of weights and basis function widths to provide robustness to optical system imperfections and system noise. The optical system computes the Euclidean distances between a 100-dimensional input vector and 198 stored reference patterns in parallel by using dual vector–matrix multipliers and a contrast-reversing spatial light modulator. Software is used to emulate an electronic chip that performs the on-line learning of the weights and basis function widths. An experimental recognition rate of 92.7% correct out of 300 testing samples is achieved with the adaptive training, versus 31.0% correct for nonadaptive training. We compare the experimental results with a detailed computer model of the system in order to analyze the influence of various noise sources on the system performance.

Original languageEnglish (US)
Pages (from-to)7545-7555
Number of pages11
JournalApplied optics
Issue number32
StatePublished - Nov 1995


  • Optical neural networks
  • Pattern recognition
  • Radial basis functions

ASJC Scopus subject areas

  • Atomic and Molecular Physics, and Optics
  • Engineering (miscellaneous)
  • Electrical and Electronic Engineering


Dive into the research topics of 'Adaptive, optical, radial basis function neural network for handwritten digit recognition'. Together they form a unique fingerprint.

Cite this