Author(s): Abdelhadi Lotfi | Abdelkader Benyettou
Journal: Journal of Artificial Intelligence
ISSN 1994-5450
Volume: 4;
Issue: 4;
Start page: 288;
Date: 2011;
VIEW PDF
DOWNLOAD PDF 
Original page
Keywords: digit recognition | probabilistic neural network | Pattern recognition | classification | MINST database
ABSTRACT
Artificial neural networks are well known in the field of pattern recognition and machine learning. Multi-layer neural networks are usually used as universal neural classifiers even though probabilistic neural networks represent a special type of artificial neural networks and have been designed to be used mainly in classification problems. In this article a study has been conducted to train a probabilistic neural network to recognize handwritten digits taken from the MINST database for handwritten digits. Results presented in this paper show good performance and generalization capacity of the proposed network for a real-world big database and no deep tuning of the parameters is required.
Journal: Journal of Artificial Intelligence
ISSN 1994-5450
Volume: 4;
Issue: 4;
Start page: 288;
Date: 2011;
VIEW PDF
DOWNLOAD PDF Original pageKeywords: digit recognition | probabilistic neural network | Pattern recognition | classification | MINST database
ABSTRACT
Artificial neural networks are well known in the field of pattern recognition and machine learning. Multi-layer neural networks are usually used as universal neural classifiers even though probabilistic neural networks represent a special type of artificial neural networks and have been designed to be used mainly in classification problems. In this article a study has been conducted to train a probabilistic neural network to recognize handwritten digits taken from the MINST database for handwritten digits. Results presented in this paper show good performance and generalization capacity of the proposed network for a real-world big database and no deep tuning of the parameters is required.