Abstract
Minimization of distortion measures requires multilayer mappings to be topographic. The author shows this only for tree-like multilayer networks. He also shows how to modify the original topographic mapping learning algorithm to increase its convergence rate. A three-layer network can form linelike feature detectors which are just as good as those in a two-layer network. However, the author finds it necessary to impose explicitly a topological constraint on the learning algorithm to obtain 'perfect' results. This constraint is equivalent to introducing the prior knowledge that the training set of images has the topology of a circle. He has also found that more careful training without this extra topological constraint also yields results of this quality.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">></ETX>
Keywords
Constraint (computer-aided design)Convergence (economics)Feature (linguistics)Computer scienceSet (abstract data type)Distortion (music)Topology (electrical circuits)Layer (electronics)Tree (set theory)Quality (philosophy)AlgorithmArtificial intelligenceMathematicsCombinatoricsGeometry
Related Publications
Self-organisation: a derivation from first principles of a class of learning algorithms
A novel derivation of T. Kohonen's topographic mapping learning algorithm (Self-Organization and Associative Memory, Springer-Verlag, 1984) is presented. Thus the author prescri...
A method of training multi-layer networks with heaviside characteristics using internal representations
A learning algorithm is presented that uses internal representations, which are continuous random variables, for the training of multilayer networks whose neurons have Heaviside...
Enhancing supervised learning algorithms via self-organization
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...
Inference aggregation detection in database management systems
The author identifies inference aggregation and cardinality aggregation as two distinct aspects of the aggregation problem. He develops the concept of a semantic relationship gr...
An improved elastic net method for the traveling salesman problem
An elastic net method is presented for finding traveling-salesman tours; the method improves on the convergence properties of a recent model proposed by R. Durbin and D. Willsha...
Publication Info
- Year
- 1988
- Type
- article
- Pages
- 93-100 vol.1
- Citations
- 14
- Access
- Closed
External Links
Social Impact
Altmetric
PlumX Metrics
Social media, news, blog, policy document mentions
Citation Metrics
14
OpenAlex
0
Influential
8
CrossRef
Cite This
Luttrell
(1988).
Self-organising multilayer topographic mappings.
IEEE International Conference on Neural Networks
, 93-100 vol.1.
https://doi.org/10.1109/icnn.1988.23833
Identifiers
- DOI
- 10.1109/icnn.1988.23833