Abstract
A shift-invariant neural network that uses the translation-invariant property of the modulus Fourier spectra with the heteroassociation interpattern association memory is proposed. A binary encoding of a spectral sampling of the training set is used to preserve the main features. Computer simulations and experimental demonstrations are provided that show the shift-invariant property of the proposed optical neural network.
Original language | English (US) |
---|---|
Pages (from-to) | 2147-2151 |
Number of pages | 5 |
Journal | Applied optics |
Volume | 33 |
Issue number | 11 |
DOIs | |
State | Published - Apr 10 1994 |
All Science Journal Classification (ASJC) codes
- Atomic and Molecular Physics, and Optics
- Engineering (miscellaneous)
- Electrical and Electronic Engineering