1990 IJCNN International Joint Conference on Neural Networks 1990
DOI: 10.1109/ijcnn.1990.137843
|View full text |Cite
|
Sign up to set email alerts
|

A new error criterion for posterior probability estimation with neural nets

Abstract: It has been shown recently that neural nets, when trained using the least squares error criterion with a desired output of 1 for belonging to a class and 0 otherwise, produce as their output an estimate of the posterior probability of the class given the input. In this paper, we introduce a new error criterion for training which improves the performance of neural nets as posterior probability estimators, when compared to using least squares. The new criterion is similar to the Kullback-Leibler information meas… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

2
34
0

Year Published

1996
1996
2013
2013

Publication Types

Select...
4
2
1

Relationship

0
7

Authors

Journals

citations
Cited by 67 publications
(36 citation statements)
references
References 4 publications
2
34
0
Order By: Relevance
“…The requirements of the application can also influence the cost selection. For instance, when relative differences are more relevant than absolute differences, cross entropy could be preferred to quadratic cost, as the simulations reported in [19] show. A large comparative work has been carried out in the literature showing the advantages of the cross entropy over the quadratic cost.…”
Section: Discussionmentioning
confidence: 99%
See 3 more Smart Citations
“…The requirements of the application can also influence the cost selection. For instance, when relative differences are more relevant than absolute differences, cross entropy could be preferred to quadratic cost, as the simulations reported in [19] show. A large comparative work has been carried out in the literature showing the advantages of the cross entropy over the quadratic cost.…”
Section: Discussionmentioning
confidence: 99%
“…A cost function is said to be SSB if has a unique minimum in when the outputs are the a posteriori probabilities of class 1, i.e., (10) According to the above definitions, an SSB detector requires an SSB cost function. For instance, the well-known crossentropy (logarithmic cost) function given by (11) is SSB [19], [20]. Not every cost function is SSB, for instance, an norm is SSB only for [4], [21].…”
Section: Problem Formulationmentioning
confidence: 99%
See 2 more Smart Citations
“…The algorithm used for training with the Cross-Entropy error is the one described in [43], while the algorithm used for training with the Sum-of-Squares error and the Minkowski error (R = 1), is the Conjugate Gradient method [44].…”
Section: Detectors Architecture Training and Test Parametersmentioning
confidence: 99%