1990
DOI: 10.1364/ao.29.004790
|View full text |Cite
|
Sign up to set email alerts
|

Parallel distributed processing model with local space-invariant interconnections and its optical architecture

Abstract: This paper proposes a parallel distributed processing model with local space-invariant interconnections, which is more readily implemented by optics and is able to classify patterns correctly, even if they have been shifted or distorted. Error backpropagation is used as a training algorithm. Computer simulation results presented indicate that the processing is effective and the network can deal with the shifted or distorted patterns. Moreover, the optical implementation architecture using matched filters for t… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

0
98
0

Year Published

1994
1994
2022
2022

Publication Types

Select...
8
2

Relationship

0
10

Authors

Journals

citations
Cited by 197 publications
(98 citation statements)
references
References 9 publications
0
98
0
Order By: Relevance
“…A parallel study of Zhang et al . [6] used a shift-invariant artificial neural network (SIANN) to recognize characters from an image. However, due to the lack of large training data and computing power at that time, their networks can not perform well on more complex problems, e.g., large-scale image and video classification.…”
Section: Introductionmentioning
confidence: 99%
“…A parallel study of Zhang et al . [6] used a shift-invariant artificial neural network (SIANN) to recognize characters from an image. However, due to the lack of large training data and computing power at that time, their networks can not perform well on more complex problems, e.g., large-scale image and video classification.…”
Section: Introductionmentioning
confidence: 99%
“…It is a deformation of multilayer perceptron, mainly used to reduce the image preprocessing work. Such networks are characterized by weight sharing and image translation invariance [33,34].…”
Section: B Convolutional Neural Networkmentioning
confidence: 99%
“…1 . It consists of three sections: preprocessing, processing by using the shift-invariant neural network [6][7][8], and postprocessing. In the preprocessing stage, original chest images are shrunk in order to decrease the computation time.…”
Section: Algorithm For Detection Of Lung Structuresmentioning
confidence: 99%