Recognition ability of the fully connected Hopfield neural network under a persistent stimulus field

Vieira, Vinı́cius; Lyra, M. L.; Silva, C.R. da

doi:10.1016/j.physa.2008.12.025

Search citation statements

Order By: Relevance

Paper Sections

Select...

Fig5 a Discrete Hopfield Neural Network1

Classification For the Pending Recognition Samples1

Citation Types

Supporting

Mentioning

Contrasting

Year Published

2010

Publication Types

Select...

Other1

Relationship

Self Cite0

Independent1

Authors

Journals

Cited by 1 publication

(2 citation statements)

References 54 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Because of the advantage of the associational memory function of the Hopfield neural network [3] , the difficulties of recognition and identification for the sparse dot-matrix characters can be overcome commendably. The first thing of the basic method is ascertain the weight coefficient of the network by means of a study or training course.…”

Section: Fig5 a Discrete Hopfield Neural Networkmentioning

confidence: 99%

“…In this application, after 3 iterative calculating repetition, rthe output of the Hopfield nerve network will be where the superscript (3) means the third iterative calculating result, not the power exponent. The Y (3) should be taken to compare with each standard character samples, then the most adjacent shape should be the right character.…”

Section: Classification For the Pending Recognition Samplesmentioning

confidence: 99%

See 1 more Smart Citation

Image recognition technique for dot-matrix character on piston surface based on Hopfield neural network method

Xin-xiang

2010

2010 International Conference on Audio, Language and Image Processing

View full text Add to dashboard Cite

In this paper, an image recognition technique for dot-matrix character on piston surface based on Hopfield neural network method is proposed. The overall structure presentation of the measuring device, the difficulties of recognition technique about the sparse dot-matrix character and the spray-ink character, the actualization of the training and the classification with Hopfield neural network method, the operation control process of automatic detection etc., are all discussed. Meanwhile, the experiment results in production line are presented as well.

show abstract

Section: Fig5 a Discrete Hopfield Neural Networkmentioning

confidence: 99%

Section: Classification For the Pending Recognition Samplesmentioning

confidence: 99%