Radial basis function network
In the field of mathematical modeling, a radial basis function network is an artificial neural network that uses radial basis functions as activation functions. The output of the network is a linear combination of radial basis functions of the inputs and neuron parameters. Radial basis function networks have many uses, including function approximation, time series prediction, classification, and system control. They were first formulated in a 1988 paper by Broomhead and Lowe, both researchers at the Royal Signals and Radar Establishment.
- Abstraction100002137
- Act100030358
- Activity100407535
- Algorithm105847438
- Broadcaster
- Communication100033020
- ComputerArchitecture106725249
- Description106724763
- Event100029378
- Message106598915
- NeuralNetwork106725467
- Procedure101023820
- PsychologicalFeature100023100
- Rule105846932
- Specification106725067
- Statement106722453
- WikicatArtificialNeuralNetworks
- WikicatClassificationAlgorithms
- YagoPermanentlyLocatedEntity
- Align
- enright
- Caption
- enFour normalized radial basis functions in one input dimension. The fourth basis function has center at . Note that the first basis function has become localized.
- enThree normalized radial basis functions in one input dimension. The additional basis function has center at
- enTwo normalized radial basis functions in one input dimension . The basis function centers are located at and .
- Comment
- enIn the field of mathematical modeling, a radial basis function network is an artificial neural network that uses radial basis functions as activation functions. The output of the network is a linear combination of radial basis functions of the inputs and neuron parameters. Radial basis function networks have many uses, including function approximation, time series prediction, classification, and system control. They were first formulated in a 1988 paper by Broomhead and Lowe, both researchers at the Royal Signals and Radar Establishment.
- Depiction
- Direction
- envertical
- Has abstract
- enIn the field of mathematical modeling, a radial basis function network is an artificial neural network that uses radial basis functions as activation functions. The output of the network is a linear combination of radial basis functions of the inputs and neuron parameters. Radial basis function networks have many uses, including function approximation, time series prediction, classification, and system control. They were first formulated in a 1988 paper by Broomhead and Lowe, both researchers at the Royal Signals and Radar Establishment.
- Hypernym
- Network
- Image
- enNormalized radial basis functions.svg
- 3
- 4
- Is primary topic of
- Radial basis function network
- Label
- enRadial basis function network
- Link from a Wikipage to an external page
- eprints.soton.ac.uk/251135/1/00080341.pdf
- ieeexplore.ieee.org/xpl/freeabs_all.jsp%3Farnumber=137644
- web.archive.org/web/20070302175857/http:/www.ki.inf.tu-dresden.de/~fritzke/FuzzyPaper/node5.html
- courses.cs.tamu.edu/rgutier/cpsc636_s10/poggio1990rbf2.pdf
- Link from a Wikipage to another Wikipage
- Activation function
- Artificial neural network
- Backpropagation
- Bayes theorem
- Category:Classification algorithms
- Category:Computational statistics
- Category:Machine learning algorithms
- Category:Neural network architectures
- Category:Regression analysis
- Cerebellar model articulation controller
- Chaos theory
- Compact space
- Control theory
- Data clustering
- Euclidean distance
- File:060728b unnormalized basis function phi.png
- File:060731 logistic map time series 2.png
- File:060808 control of logistic map.svg
- File:Chaotic Time Series Prediction.svg
- File:Normalized basis functions.png
- File:Rbf-network.svg
- File:Unnormalized radial basis functions.svg
- Forward problem
- Function approximation
- Gradient descent
- Hierarchical RBF
- In Situ Adaptive Tabulation
- Instance-based learning
- Instantaneously trained neural networks
- Inverse problem
- K-means clustering
- Kronecker delta function
- Learning rate
- Linear combination
- Local linearity
- Logistic function
- Logistic map
- Lyapunov exponent
- Mahalanobis distance
- Mathematical modeling
- Mean squared error
- Newton's method
- Norm (mathematics)
- Normal distribution
- Population dynamics
- Predictive analytics
- Pseudoinverse
- Radial basis function
- Radial basis function kernel
- Regularization (machine learning)
- Roger Jones (physicist and entrepreneur)
- Royal Signals and Radar Establishment
- Scalar (mathematics)
- Statistical classification
- Stochastic kernel
- Time series prediction
- Universal approximator
- Unsupervised learning
- Vector (geometric)
- SameAs
- 2Wbe5
- m.02pn52m
- Q2679684
- Radial basis function network
- Rete neurale a base radiale
- RNA de base radial
- Sieć radialna
- Мережа радіальних базисних функцій
- Сеть радиально-базисных функций
- 径向基函数网络
- Subject
- Category:Classification algorithms
- Category:Computational statistics
- Category:Machine learning algorithms
- Category:Neural network architectures
- Category:Regression analysis
- Thumbnail
- WasDerivedFrom
- Radial basis function network?oldid=1124943010&ns=0
- Width
- 250
- WikiPageLength
- 30278
- Wikipage page ID
- 9651443
- Wikipage revision ID
- 1124943010
- WikiPageUsesTemplate
- Template:Cite book
- Template:Editorializing
- Template:Multiple images
- Template:Reflist
- Template:Short description
