Abstract | ||
---|---|---|
Feedforward neural networks trained to solve classification problems define an approximation of the conditional probabilities P(Ci,|x) if the output units correspond to categories Ci. The present paper shows that if a least mean squared error cost function is minimised during training phase, the resulting approximation of the P(Ci|x)s is poor in the ranges of the input variable x where the conditional probabilities take on very low values. The use of the Kullback-Leibler distance measure is proposed to overcome this limitation; a cost function derived from this information theoretic measure is defined and a computationally light training procedure is derived in the case of binary classification problems. The effectiveness of the proposed procedure is verified by means of comparative experiments. |
Year | DOI | Venue |
---|---|---|
1996 | 10.1016/0925-2312(96)00025-2 | Neurocomputing |
Keywords | Field | DocType |
Feedforward neural networks,Classification,Kullback-Leibler distance | Feedforward neural network,Conditional probability,Binary classification,Pattern recognition,Mean squared error,Artificial intelligence,Machine learning,Kullback–Leibler divergence,Mathematics | Journal |
Volume | Issue | ISSN |
13 | 2-4 | 0925-2312 |
Citations | PageRank | References |
1 | 0.41 | 9 |
Authors | ||
2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Pietro Burrascano | 1 | 21 | 4.77 |
Dario Pirollo | 2 | 2 | 0.77 |