Modified high-order neural network for invariant pattern recognition

Evgeny Artyomov, Orly Yadid-Pecht

Research output: Contribution to journalArticlepeer-review

55 Scopus citations


A modification for high-order neural networks (HONN) is described. The proposed modified HONN takes into account prior knowledge of the binary patterns that must be learned. This significantly reduces hence computation time as well as memory requirements for network configuration and weight storage. An "approximately equal triangles" scheme for weight sharing is also proposed. These modifications enable the efficient computation of HONNs for image fields of greater that 100 × 100 pixels without any loss of pattern information.

Original languageEnglish
Pages (from-to)843-851
Number of pages9
JournalPattern Recognition Letters
Issue number6
StatePublished - 1 May 2005


  • Binary patterns
  • HONN
  • High-order neural networks
  • Invariant pattern recognition

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Computer Vision and Pattern Recognition
  • Artificial Intelligence


Dive into the research topics of 'Modified high-order neural network for invariant pattern recognition'. Together they form a unique fingerprint.

Cite this