Abstract:
The main motivation of this paper is to design a statistically well justified and biologically compatible neural network model and, in particular, to suggest a theoretical interpretation of the well known high parallelism of biological neural networks. We consider a novel probabilistic approach to neural networks developed in the framework of statistical pattern recognition, and refer to a series of theoretical results published earlier. It is shown that the proposed parallel fusion of probabilistic neural networks produces biologically plausible structures and improves the resulting recognition performance. The complete design methodology based on the EM algorithm has been applied to recognise unconstrained handwritten numerals from the database of Concordia University Montreal. We achieved a recognition accuracy of about 95%, which is comparable with other published results.
Similar content being viewed by others
Author information
Authors and Affiliations
Additional information
Received: 21 November 2000, Received in revised form: 15 November 2001, Accepted: 13 December 2001
Rights and permissions
About this article
Cite this article
Grim, J., Kittler, J., Pudil, P. et al. Multiple Classifier Fusion in Probabilistic Neural Networks. Pattern Anal Appl 5, 221–233 (2002). https://doi.org/10.1007/s100440200020
Issue Date:
DOI: https://doi.org/10.1007/s100440200020