Keywords
Upper and lower boundsPerceptronRepresentation (politics)Function (biology)Artificial neural networkMathematicsArtificial intelligenceComputer scienceAlgorithmApplied mathematicsPattern recognition (psychology)Mathematical analysis
Affiliated Institutions
Related Publications
Improving the learning speed of 2-layer neural networks by choosing initial values of the adaptive weights
The authors describe how a two-layer neural network can approximate any nonlinear function by forming a union of piecewise linear segments. A method is given for picking initial...
A training algorithm for optimal margin classifiers
A training algorithm that maximizes the margin between the training patterns and the decision boundary is presented. The technique is applicable to a wide variety of the classif...
Circular backpropagation networks for classification
The class of mapping networks is a general family of tools to perform a wide variety of tasks. This paper presents a standardized, uniform representation for this class of netwo...
Neural Network Classifiers Estimate Bayesian <i>a posteriori</i> Probabilities
Many neural network classifiers provide outputs which estimate Bayesian a posteriori probabilities. When the estimation is accurate, network outputs can be treated as probabilit...
Using random weights to train multilayer networks of hard-limiting units
A gradient descent algorithm suitable for training multilayer feedforward networks of processing units with hard-limiting output functions is presented. The conventional backpro...
Publication Info
- Year
- 1986
- Type
- review
- Volume
- 53
- Issue
- 4
- Pages
- 203-217
- Citations
- 69
- Access
- Closed
External Links
Social Impact
Altmetric
PlumX Metrics
Social media, news, blog, policy document mentions
Citation Metrics
69
OpenAlex
Cite This
Steven E. Hampson,
Dennis J. Volper
(1986).
Linear function neurons: Structure and training.
Biological Cybernetics
, 53
(4)
, 203-217.
https://doi.org/10.1007/bf00336991
Identifiers
- DOI
- 10.1007/bf00336991