Finding Optimal Neural Networks for Land Use Classification

Horst Bischof, Ales Leonardis

Research output: Contribution to journalArticlepeer-review


The authors present a fully automatic and computationally efficient algorithm based on the minimum description length principle (MDL) for optimizing multilayer perceptron (MLP) classifiers. They demonstrate their method on the problem of multispectral Landsat image classification. They compare their results with a hand-designed MLP and a Gaussian maximum likelihood classifier, in which their method produces better classification accuracy with a smaller number of hidden units.
Original languageEnglish
Pages (from-to)337-341
JournalIEEE Transactions on Geoscience and Remote Sensing
Issue number1
Publication statusPublished - 1998


Dive into the research topics of 'Finding Optimal Neural Networks for Land Use Classification'. Together they form a unique fingerprint.

Cite this