Analysis of hidden units in a layered network trained to classify sonar targets

Neural NetworksPublished 1 January 1988

Rebecca Gorman, Terrence J. Sejnowski

DOI10.1016/0893-6080(88)90023-8

Source URL

Citations1,111

SJR quartileQ1

SJR score1.49

SNIP2.02

TL;DR

A neural network learning procedure has been applied to the classification of sonar returns from two undersea targets, a metal cylinder and a similarly shaped rock, and network performance and classification strategy was comparable to that of trained human listeners.

Abstract

A neural network learning procedure has been applied to the classification of sonar returns from two undersea targets, a metal cylinder and a similarly shaped rock. Networks with an intermediate layer of hidden processing units achieved a classification accuracy as high as 100% on a training set of 104 returns. These networks correctly classified up to 90.4% of 104 test returns not contained in the training set. This performance was better than that of a nearest neighbor classifier, which was 82.7%, and was close to that of an optimal Bayes classifier. Specific signal features extracted by hidden units in a trained network were identified and related to coding schemes in the pattern of connection strengths between the input and the hidden units. Network performance and classification strategy was comparable to that of trained human listeners.

Keywords

Computer ScienceEarth and Planetary SciencesEngineering

Learning Internal Representations by Error Propagation

16,235 Citations1985David E. Rumelhart, Geoffrey E. Hinton +1 more

IEEE Transactions on Information TheoryNearest neighbor pattern classification

16,134 Citations1967Thomas M. Cover, Peter E. Hart

The nearest neighbor decision rule assigns to an unclassified sample point the classification of the nearest of a set of previously classified points, so it may be said that half the classification information in an infinite sample set is contained in the nearest neighbor.

IEEE ASSP MagazineAn introduction to computing with neural nets

7,858 Citations1987Richard P. Lippmann

PsychometrikaHierarchical Clustering Schemes

4,891 Citations1967S. C. Johnson

A useful correspondence is developed between any hierarchical system of such clusters, and a particular type of distance measure, that gives rise to two methods of clustering that are computationally rapid and invariant under monotonic transformations of the data.

Parallel Networks that Learn to Pronounce English Text

1,556 Citations1989Terrence J. Sejnowski

University of North Texas Digital Library (University of North Texas)Nonlinear signal processing using neural networks: Prediction and system modelling

375 Citations1987Alan S. Lapedes

It is demonstrated that the backpropagation learning algorithm for neural networks may be used to predict points in a highly chaotic time series with orders of magnitude increase in accuracy over conventional methods including the Linear Predictive Method and the Gabor-Volterra-Weiner Polynomial Method.

View PDF

IEEE Transactions on Information TheoryBibliography on estimation of misclassification

307 Citations1974Godfried Toussaint

Articles, books, and technical reports on the theoretical and experimental estimation of probability of misclassification are listed for the case of correctly labeled or preclassified training data.

IEEE Transactions on Acoustics Speech and Signal ProcessingLearned classification of sonar targets using a massively parallel network

246 Citations1988Rebecca Gorman, Terrence J. Sejnowski

The performance of a three-layered network was better than trained human listeners and the network generalized better than a nearest-neighbor classifier.

Physica D Nonlinear PhenomenaLearning symmetry groups with hidden units: Beyond the perceptron

93 Citations1986Terrence J. Sejnowski, Paul K. Kienker +1 more

It is demonstrated that the Boltzmann learning algorithm is capable of finding sets of weights which turn hidden units into useful higher-order feature detectors capable of solving symmetry problems.

View PDF