Analog design of a new neural network for optical character recognition

Analog design of a new neural network for optical character recognition

An electronic circuit is presented for a new type of neural network, which gives a recognition rate of over 100 kHz. The network is used to classify handwritten numerals, presented as Fourier and wavelet descriptors, and has been shown to train far quicker than the popular backpropagation network wh...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on neural networks 1999, Vol.10 (4), p.951-953
Hauptverfasser: Morns, I.P., Dlay, S.S.
Format: Artikel
Sprache:eng
Schlagworte:
Analog circuits
Applied sciences
Artificial intelligence
Backpropagation
Character recognition
Circuit properties
Classification
Computer science
control theory
systems
Connectionism. Neural networks
Electric, optical and optoelectronic circuits
Electronic circuits
Electronics
Exact sciences and technology
Fourier analysis
Negative feedback
Networks
Neural networks
Neurons
Optical character recognition
Optical character recognition software
Optical computing
Optical design
Optical fiber networks
Pattern recognition. Digital image processing. Computational geometry
Recognition
Trains
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:An electronic circuit is presented for a new type of neural network, which gives a recognition rate of over 100 kHz. The network is used to classify handwritten numerals, presented as Fourier and wavelet descriptors, and has been shown to train far quicker than the popular backpropagation network while maintaining classification accuracy.
ISSN:1045-9227
1941-0093
DOI:10.1109/72.774269