A neural network with competitive layers for character recognition
Goltsev, Alexander (National Academy of Sciences of Ukraine)
Gritsenko, Vladimir (National Academy of Sciences of Ukraine)

Fecha:	2022
Resumen:	A structure and functioning mechanisms of a neural network with competitive layers are described. The network is intended to solve the character recognition task. The network consists of several competitive layers of neurons. Each layer is a neural network consisting of a number of neurons represented as a layer. The number of neural layers is equal to the number of recognized classes. All neural layers have one-to-one correspondence with one another and with the input raster. The neurons of every layer have mutual lateral learning connections, which weights are modified during the learning process. There is a competitive (inhibitory) relationship between all neural layers. This competitive interaction is realized by means of a "winner-take-all" (WTA) procedure which aim is to select the layer with the highest level of neural activity. Validation of the network has been done in experiments on recognition of handwritten digits of the MNIST database. The experiments have demonstrated that its error rate is few less than 2%, which is not a high result, but it is compensated by rather fast data processing and a very simple structure and functioning mechanisms.
Derechos:	Aquest document està subjecte a una llicència d'ús Creative Commons. Es permet la reproducció total o parcial, la distribució, i la comunicació pública de l'obra, sempre que no sigui amb finalitats comercials, i sempre que es reconegui l'autoria de l'obra original. No es permet la creació d'obres derivades.
Lengua:	Anglès
Documento:	Article ; Versió publicada
Materia:	Pattern recognition ; Learning ; Classification ; Character and text recognition ; Handwriting recognition ; Neural networks ; Character recognition ; Machine learning
Publicado en:	ELCVIA. Electronic letters on computer vision and image analysis, Vol. 21 Núm. 1 (2022) , p. 102-110 (Regular Issue) , ISSN 1577-5097

Adreça original: https://elcvia.cvc.uab.cat/article/view/1392
DOI: 10.5565/rev/elcvia.1392

9 p, 170.4 KB

El registro aparece en las colecciones:
Artículos > Artículos publicados > ELCVIA