Optical analog of two-dimensional neural networks and their application in recognition of radar targets
- 1 January 1986
- proceedings article
- Published by AIP Publishing in AIP Conference Proceedings
- Vol. 151 (1) , 146-152
- https://doi.org/10.1063/1.36272
Abstract
Optical analogs of 2−D distribution of idealized neurons (2−D neural net) based on partitioning of the resulting 4−D connectivity matrix are discussed. These are desirable because of compatibility with 2−D feature spaces and ability to realize denser networks. An example of their use with sinogram classifiers derived from ralistic radar data of scale models of three aerospace objects as learning set is given. Super‐resolved recognition from partial information that can be as low as 20% of the sinogram data is demonstrated together with a capacity for error correction and generalization.Keywords
This publication has 0 references indexed in Scilit: