Open AccessProceedings Article
Supervised Learning with Growing Cell Structures
Bernd Fritzke
- 29 Nov 1993
- Vol. 6, pp 255-262
TL;DR: A new incremental radial basis function network suitable for classification and regression problems, which needs few training epochs and seems to generalize very well.
read more
Abstract: We present a new incremental radial basis function network suitable for classification and regression problems. Center positions are continuously updated through soft competitive learning. The width of the radial basis functions is derived from the distance to topological neighbors. During the training the observed error is accumulated locally and used to determine where to insert the next unit. This leads (in case of classification problems) to the placement of units near class borders rather than near frequency peaks as is done by most existing methods. The resulting networks need few training epochs and seem to generalize very well. This is demonstrated by examples.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
•Proceedings Article
A Growing Neural Gas Network Learns Topologies
Bernd Fritzke
- 01 Jan 1994
TL;DR: An incremental network model is introduced which is able to learn the important topological relations in a given set of input vectors by means of a simple Hebb-like learning rule.
Regularization in the selection of radial basis function centers
TL;DR: An efficient implementation of RFS into which either delete-1 or generalized cross-validation can be incorporated and a reestimation formula for the regularization parameter are also discussed.
382
Using Radial Basis Function Networks for Function Approximation and Classification
TL;DR: Many aspects associated with the RBF network, such as network structure, universal approimation capability, radial basis functions,RBF network learning, structure optimization, normalized RBF networks, application to dynamic system modeling, and nonlinear complex-valued signal processing, are described.
An integrated trust and reputation model for open multi-agent systems
Trung Dong Huynh,Nicholas R. Jennings,Nigel Shadbolt +2 more
TL;DR: Fire, a trust and reputation model that integrates a number of information sources to produce a comprehensive assessment of an agent’s likely performance in open systems, is presented and is shown to help agents gain better utility than their benchmarks.
215
Decision trees can initialize radial-basis function networks
TL;DR: This paper addresses issues by initializing RBF networks with decision trees that define relatively pure regions in the instance space; each of these regions then determines one basis function.
133
References
•Proceedings Article
The Cascade-Correlation Learning Architecture
Scott E. Fahlman,Christian Lebiere +1 more
- 01 Jan 1989
TL;DR: The Cascade-Correlation architecture has several advantages over existing algorithms: it learns very quickly, the network determines its own size and topology, it retains the structures it has built even if the training set changes, and it requires no back-propagation of error signals through the connections of the network.
A resource-allocating network for function interpolation
TL;DR: A network that allocates a new computational unit whenever an unusual pattern is presented to the network, which learns much faster than do those using backpropagation networks and uses a comparable number of synapses.
Growing cell structures—a self-organizing network for unsupervised and supervised learning
TL;DR: A new self-organizing neural network model that has two variants that performs unsupervised learning and can be used for data visualization, clustering, and vector quantization is presented and results on the two-spirals benchmark and a vowel classification problem are presented that are better than any results previously published.
1.3K
Regularization algorithms for learning that are equivalent to multilayer networks.
Tomaso Poggio,Federico Girosi +1 more
TL;DR: A theory is reported that shows the equivalence between regularization and a class of three-layer networks called regularization networks or hyper basis functions.
1.1K
Learning to tell two spirals apart
K. Lang
- 01 Jan 1988
TL;DR: A networkarchitecture is exhibited that facilitates the learning of the spiral task, and the leaming speed of several variants of the back-propagation algorithm is compared.
482