Neural network classification: a Bayesian interpretation
- 1 January 1990
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks
- Vol. 1 (4) , 303-305
- https://doi.org/10.1109/72.80269
Abstract
The relationship between minimizing a mean squared error and finding the optimal Bayesian classifier is reviewed. This provides a theoretical interpretation for the process by which neural networks are used in classification. A number of confidence measures are proposed to evaluate the performance of the neural network classifier within a statistical framework.Keywords
This publication has 3 references indexed in Scilit:
- Learning in Artificial Neural Networks: A Statistical PerspectiveNeural Computation, 1989
- Consistent inference of probabilities in layered networks: predictions and generalizationsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1989
- Parallel Distributed ProcessingPublished by MIT Press ,1986