Abstract
A neural network processing scheme is proposed which utilizes a self-organizing Kohonen feature map as the front end to a feedforward classifier network. The results of a series of benchmarking studies based upon artificial statistical pattern recognition tasks indicate that the proposed architecture performs significantly better than do conventional feedforward classifier networks when the decision regions are disjoint. This is attributed to the fact that the self-organization process allows internal units in the succeeding classifier network to be sensitive to a specific set of features in the input space at the outset of training.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">></ETX>
Keywords
Computer scienceArtificial intelligenceDisjoint setsSelf-organizing mapClassifier (UML)Artificial neural networkFeed forwardBenchmarkingMachine learningSelf-organizationPattern recognition (psychology)Data miningAlgorithmMathematicsEngineering
Affiliated Institutions
Related Publications
Reducing transmission error effects using a self-organizing network
The author shows that a Kohonen self-organizing network can be used to reduce the effects of errors in digital transmission of speech, Kohonen learning is used to cause the netw...
The self-organizing map
The self-organized map, an architecture suggested for artificial neural networks, is explained by presenting simulation experiments and practical applications. The self-organizi...
Layered neural nets for pattern recognition
A pattern recognition concept involving first an 'invariance net' and second a 'trainable classifier' is proposed. The invariance net can be trained or designed to produce a set...
BPS: a learning algorithm for capturing the dynamic nature of speech
A novel backpropagation learning algorithm for a particular class of dynamic neural networks in which some units have a local feedback is proposed. Hence these networks can be t...
Neural network ensembles
Several means for improving the performance and training of neural networks for classification are proposed. Crossvalidation is used as a tool for optimizing network parameters ...
Publication Info
- Year
- 1989
- Type
- article
- Volume
- i
- Pages
- 523-530 vol.2
- Citations
- 20
- Access
- Closed
External Links
Social Impact
Altmetric
PlumX Metrics
Social media, news, blog, policy document mentions
Citation Metrics
20
OpenAlex
0
Influential
11
CrossRef
Cite This
Holdaway
(1989).
Enhancing supervised learning algorithms via self-organization.
International Joint Conference on Neural Networks
, i
, 523-530 vol.2.
https://doi.org/10.1109/ijcnn.1989.118293
Identifiers
- DOI
- 10.1109/ijcnn.1989.118293