Backpropagation uses prior information efficiently
- 1 January 1993
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks
- Vol. 4 (5) , 794-802
- https://doi.org/10.1109/72.248457
Abstract
The ability of neural net classifiers to deal with a priori information is investigated. For this purpose, backpropagation classifiers are trained with data from known distributions with variable a priori probabilities, and their performance on separate test sets is evaluated. It is found that backpropagation employs a priori information in a slightly suboptimal fashion, but this does not have serious consequences on the performance of the classifier. Furthermore, it is found that the inferior generalization that results when an excessive number of network parameters are used can (partially) be ascribed to this suboptimality.Keywords
This publication has 10 references indexed in Scilit:
- Neural Network Classifiers Estimate Bayesian a posteriori ProbabilitiesNeural Computation, 1991
- Performance and generalization of the classification figure of merit criterion functionIEEE Transactions on Neural Networks, 1991
- The multilayer perceptron as an approximation to a Bayes optimal discriminant functionIEEE Transactions on Neural Networks, 1990
- Neural network classification: a Bayesian interpretationIEEE Transactions on Neural Networks, 1990
- Phoneme recognition using time-delay neural networksIEEE Transactions on Acoustics, Speech, and Signal Processing, 1989
- A comparison between criterion functions for linear classifiers, with an application to neural netsIEEE Transactions on Systems, Man, and Cybernetics, 1989
- Universal approximation using feedforward networks with non-sigmoid hidden layer activation functionsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1989
- A novel objective function for improved phoneme recognition using time delay neural networksPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1989
- On the capabilities of multilayer perceptronsJournal of Complexity, 1988
- Restart procedures for the conjugate gradient methodMathematical Programming, 1977