Learning criteria for training neural network classifiers

  title={Learning criteria for training neural network classifiers},
  author={Ping Zhou and Jim Austin},
  journal={Neural Computing & Applications},
This paper presents a study of two learning criteria and two approaches to using them for training neural network classifiers, specifically a Multi-Layer Perceptron (MLP) and Radial Basis Function (RBF) networks. The first approach, which is a traditional one, relies on the use of two popular learning criteria, i.e. learning via minimising a Mean Squared Error (MSE) function or a Cross Entropy (CE) function. It is shown that the two criteria have different charcteristics in learning speed and… CONTINUE READING


Publications citing this paper.
Showing 1-10 of 10 extracted citations

Unsupervised Feature Learning Based on Deep Models for Environmental Audio Tagging

IEEE/ACM Transactions on Audio, Speech, and Language Processing • 2017
View 6 Excerpts
Highly Influenced

Multi user detection in CDMA system using Linear and Nonlinear Detector

Sandigdha Acharya International, sandigdhaacharya
View 2 Excerpts


Publications referenced by this paper.
Showing 1-10 of 18 references

Neural networks for pattern recognition

CM Bishop
View 5 Excerpts
Highly Influenced

On the probabilistic interpretation of neural network classifiers and discriminative training criteria

H. Hey
IEEE Trans Pattern Analysis and Machine Intelligence • 1995
View 4 Excerpts
Highly Influenced

Convergence of back-propagation in neural networks using a log-likelihood function

MJJ Holt, S. Semnani
Electronic Letters • 1990
View 5 Excerpts
Highly Influenced

Probabilistic interpretation of feedforward classification networks outputs, with relationships to statistical pattern recognition

JS Bridle
Soulie F, J. Herault J (eds) Neuro-computing: Algorithms, architectures and applications, • 1990
View 5 Excerpts
Highly Influenced

Austin misclassification error with minimumcomplexity networks

Neural Networks • 1994

A novel multilayer neural networks training algorithm that minimises the probability of classification errors

V. Nedljkovid
IEEE Trans Neural Networks • 1993
View 2 Excerpts

Similar Papers

Loading similar papers…