Finding optimal neural networks for land use classification
IEEE Transactions on Geoscience and Remote SensingPublished 1 January 1998
Horst Bischof, Aleš Leonardis
Citations61
SJR quartileQ1
SJR score2.40
SNIP2.37
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
The authors present a fully automatic and computationally efficient algorithm based on the minimum description length principle (MDL) for optimizing multilayer perceptron (MLP) classifiers and compare their results with a hand-designed MLP and a Gaussian maximum likelihood classifier.
Abstract
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.
Keywords
Computer ScienceEngineeringEnvironmental Science
Pattern classification and scene analysis
12,643 Citations1973Richard O. Duda, Peter E. Hart
Tabu Search
5,702 Citations1997Fred Glover, Manuel Laguna
Modern heuristic techniques for combinatorial problems
2,623 Citations1993Colin R. Reeves
This chapter discusses combinatorial problems local and global optima heuristics, the tabu framework, and Evaluation of heuristic performance: analytical methods empirical testing statistical inference conclusions.
Optimal Brain Damage
2,613 Citations1989Yann LeCun, John S. Denker +1 more
A class of practical and nearly optimal schemes for adapting the size of a neural network by using second-derivative information to make a tradeoff between network complexity and training set error is derived.
The Caltech Institute Archives (California Institute of Technology)Second order derivatives for network pruning: Optimal Brain Surgeon
1,489 Citations1992Babak Hassibi, David G. Stork
Of OBS, Optimal Brain Damage, and magnitude-based methods, only OBS deletes the correct weights from a trained XOR network in every case, and thus yields better generalization on test data.
Choice Reviews OnlineNeural networks for optimization and signal processing
1,192 Citations1993
A guide to the fundamental mathematics of neurocomputing, a review of neural network models and an analysis of their associated algorithms, and state-of-the-art procedures to solve optimization problems are explained.
Research Showcase @ Carnegie Mellon University (Carnegie Mellon University)Distributed representations
1,043 Citations2014Geoffrey E. Hinton
IEEE Transactions on Information TheoryUniversal coding, information, prediction, and estimation
903 Citations1984J. Rissanen
A connection between universal codes and the problems of prediction and statistical estimation is established, and a known lower bound for the mean length of universal codes is sharpened and generalized, and optimum universal codes constructed.
IEEE Transactions on Geoscience and Remote SensingMultispectral classification of Landsat-images using neural networks
407 Citations1992Horst Bischof, W. X. Schneider +1 more
Three-layer back-propagation networks for classification of Landsat TM data on a pixel-by-pixel basis is reported and it is shown that the neural network is able to perform better than the maximum likelihood classifier.
Neural ComputationMeasuring the VC-Dimension of a Learning Machine
386 Citations1994Vladimir Vapnik, Esther Levin +1 more
A method for measuring the capacity of learning machines is described, based on fitting a theoretically derived function to empirical measurements of the maximal difference between the error rates on two separate data sets of varying sizes.
IEEE Transactions on Geoscience and Remote SensingMultisource classification of remotely sensed data: fusion of Landsat TM and SAR images
253 Citations1994Anne H. Schistad Solberg, Anil K. Jain +1 more
The fusion model gives significant improvements in the classification error rates compared to the conventional single-source classifiers.
International Journal of Computer VisionSegmentation of range images as the search for geometric parametric models
167 Citations1995Aleš Leonardis, Alok Gupta +1 more
A new paradigm for the segmentation of range images into piecewise continuous surfaces is presented through an effective combination of simple component algorithms, which stands in contrast to methods which attempt to solve the problem in a single processing step using sophisticated means.
IEEE Transactions on Geoscience and Remote SensingApplication of neural networks to radar image classification
140 Citations1994Y. Hara, R.G. Atkins +3 more
A new terrain classification technique is introduced to determine terrain classes in polarimetric SAR images, utilizing unsupervised neural networks to provide automatic classification, and employing an iterative algorithm to improve the performance.
Pyramidal Neural Networks
24 Citations2026Horst Bischof
This chapter discusses networks Versus Pyramids, Hierarchical Learning, and Structural Considerations, which addresses the role of hierarchy in the development of knowledge representation.
CaltechAUTHORS (California Institute of Technology)Remote Sensing Image Analysis via a Texture Classification Neural Network
8 Citations1992Hayit Greenspan, R.M. Goodman
A texture classification network is applied to remote sensing image analysis to extract the characteristics of the area depicted in the input image, thus achieving a segmented map of the region.
Complexity optimization of adaptive RBF networks
5 Citations1996Aleš Leonardis, Horst Bischof
An extension of RBF networks is proposed which includes a mechanism for optimizing the complexity of the network, and involves two procedures: adaptation (training) and selection.