Abstract
Abstract-We have applied massively parallel learning networks to the classification of sonar returns from two undersea targets and have studied the ability of networks to correctly classify both training and testing examples. Networks with an intermediate layer of hidden processing units achieved a classification accuracy as high as 100 percent on a training set of 104 returns. These networks correctly classified a test set of 104 returns not contained in the training set with an accuracy of up to 90.4 percent. Networks without an intermediate layer of processing units achieved only 73.1 percent correct on the same test set. Performance improved and the variability due to the initial conditions for training decreased with the number of hidden units. The effect of training set design on test set performance was also examined. The performance of a three-layered network was better than trained human listeners and the network generalized better than a nearest neighbor classifier.
Keywords
Test setClassifier (UML)Computer scienceSet (abstract data type)Massively parallelArtificial intelligenceSonarTraining setPattern recognition (psychology)Machine learningParallel computing
Affiliated Institutions
Related Publications
Parallel networks that learn to pronounce English text
This paper describes NETtalk, a class of massively-parallel network systems that learn to convert English text to speech. The memory representations for pronunciations are learn...
Boosting attribute and phone estimation accuracies with deep neural networks for detection-based speech recognition
Generation of high-precision sub-phonetic attribute (also known as phonological features) and phone lattices is a key frontend component for detection-based bottom-up speech rec...
Parallel Distributed Processing
What makes people smarter than computers? These volumes by a pioneering neurocomputing group suggest that the answer lies in the massively parallel architecture of the human min...
Auto-encoder bottleneck features using deep belief networks
Neural network (NN) bottleneck (BN) features are typically created by training a NN with a middle bottleneck layer. Recently, an alternative structure was proposed which trains ...
Sparse Multilayer Perceptron for Phoneme Recognition
This paper introduces the sparse multilayer perceptron (SMLP) which jointly learns a sparse feature representation and nonlinear classifier boundaries to optimally discriminate ...
Publication Info
- Year
- 1988
- Type
- article
- Volume
- 36
- Issue
- 7
- Pages
- 1135-1140
- Citations
- 242
- Access
- Closed
External Links
Social Impact
Altmetric
PlumX Metrics
Social media, news, blog, policy document mentions
Citation Metrics
242
OpenAlex
Cite This
Rebecca Gorman,
Terrence J. Sejnowski
(1988).
Learned classification of sonar targets using a massively parallel network.
IEEE Transactions on Acoustics Speech and Signal Processing
, 36
(7)
, 1135-1140.
https://doi.org/10.1109/29.1640
Identifiers
- DOI
- 10.1109/29.1640