Some extensions of radial basis functions and their applications in artificial intelligence
Computers & Mathematics with ApplicationsPublished 1 December 1992
Federico Girosi
Citations78
SJR quartileQ1
SJR score0.95
SNIP1.31
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
Some extensions of the standard theory of Radial Basis Functions are shown, introduced in order to deal with a large number of examples and with problems in which different variables play very different roles.
Abstract
Radial Basis Functions have recently found interesting applications in Artificial Intelligence, and in particular in the problem of learning to perform a particular task from a set of examples. However, in many practical cases the Radial Basis Functions method cannot be applied in a straight-forward manner, because it does not take into account some features that are typical of the problem of learning from examples. In this paper, we show some extensions of the standard theory, introduced in order to deal with a large number of examples and with problems in which different variables play very different roles. We present some examples and also point out some open problems.
Keywords
Computer SciencePhysics and Astronomy
Choice Reviews OnlineGenetic algorithms in search, optimization, and machine learning
49,278 Citations1989
This book brings together the computer techniques, mathematical tools, and research results that will enable both students and practitioners to apply genetic algorithms to problems in many fields.
ScienceOptimization by Simulated Annealing
44,600 Citations1983Scott Kirkpatrick, C. D. Gelatt +1 more
A detailed analogy with annealing in solids provides a framework for optimization of the properties of very large and complex systems.
Mathematics of Control Signals and SystemsApproximation by superpositions of a sigmoidal function
13,684 Citations1989George Cybenko
American Journal of Physics<i>Numerical Recipes, The Art of Scientific Computing</i>
10,031 Citations1987William H. Press, Brian P. Flannery +3 more
Neural NetworksOn the approximate realization of continuous mappings by neural networks
4,220 Citations1989Ken-ichi Funahashi
It is proved that any continuous mapping can be approximately realized by Rumelhart-Hinton-Williams' multilayer neural networks with at least one hidden layer whose output functions are sigmoid functions.
Neural ComputationFast Learning in Networks of Locally-Tuned Processing Units
4,219 Citations1989John Moody, Christian J. Darken
This work proposes a network architecture which uses a single internal layer of locally-tuned processing units to learn both classification tasks and real-valued function approximations (Moody and Darken 1988).
Complex SystemsRadial Basis Functions, Multi-Variable Functional Interpolation and Adaptive Networks
3,439 Citations1988David S. Broomhead, David Lowe
The relationship between 'learning' in adaptive layered networks and the fitting of data with high dimensional surfaces is discussed, leading naturally to a picture of 'generalization in terms of interpolation between known data points and suggests a rational approach to the theory of such networks.
Proceedings of the IEEENetworks for approximation and learning
3,257 Citations1990Tomaso Poggio, Federico Girosi
Regularization theory and a theoretical framework for approximation that leads to a class of three-layer networks called regularization networks are discussed, generalized to a formulation that includes task-dependent clustering and dimensionality reduction.
The MIT Press eBooksParallel Distributed Processing
3,227 Citations1987James L. McClelland, David E. Rumelhart +1 more
IEEE Transactions on Information TheoryUniversal approximation bounds for superpositions of a sigmoidal function
2,849 Citations1993Andrew R. Barron
The approximation rate and the parsimony of the parameterization of the networks are shown to be advantageous in high-dimensional settings and the integrated squared approximation error cannot be made smaller than order 1/n/sup 2/d/ uniformly for functions satisfying the same smoothness assumption.
Physica D Nonlinear PhenomenaExtracting qualitative dynamics from experimental data
2,292 Citations1986D.S. Broomhead, Gregory P. King
Computers & Mathematics with ApplicationsMultiquadrics—A scattered data approximation scheme with applications to computational fluid-dynamics—II solutions to parabolic, hyperbolic and elliptic partial differential equations
2,024 Citations1990E.J. Kansa
Physical Review LettersPredicting chaotic time series
1,945 Citations1987J. Doyne Farmer, John J. Sidorowich
An error estimate is presented for this forecasting technique for chaotic data, and its effectiveness is demonstrated by applying it to several examples, including data from the Mackey-Glass delay differential equation, Rayleigh-Benard convection, and Taylor-Couette flow.
Computers & Mathematics with ApplicationsMultiquadrics—A scattered data approximation scheme with applications to computational fluid-dynamics—I surface approximations and partial derivative estimates
1,936 Citations1990E.J. Kansa
Numerical results show that the modified MQ scheme is an excellent method not only for very accurate interpolation, but also for partial derivative estimates, and is applied to parabolic, hyperbolic and elliptic partial differential equations.
Mathematics of ComputationScattered data interpolation: tests of some methods
1,904 Citations1982Richard Franke
Parallel Networks that Learn to Pronounce English Text
1,556 Citations1989Terrence J. Sejnowski
Research Showcase @ Carnegie Mellon University (Carnegie Mellon University)ALVINN, an autonomous land vehicle in a neural network
1,430 Citations2018Dean Pomerleau
Lecture notes in mathematicsSplines minimizing rotation-invariant semi-norms in Sobolev spaces
1,361 Citations1977Jean Duchon
A family of semi-norms is defined, subject to some interpolating conditions, providing interpolation methods that preserve polynomials of degree≤m−1 and converge in Sobolev spaces Hm+s(Ω).
Neural ComputationA Resource-Allocating Network for Function Interpolation
1,359 Citations1991John Platt
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.
Physica D Nonlinear PhenomenaNonlinear prediction of chaotic time series
1,351 Citations1989Martin Casdagli
Numerical techniques are presented for constructing nonlinear predictive models directly from time series data and scaling laws are developed which describe the data requirements for reliable predictions.
Methods for Solving Incorrectly Posed Problems
1,326 Citations1984Vladimir A. Morozov
A new book enPDFd methods for solving incorrectly posed problems that can be a new way to explore the knowledge and get one thing to always remember in every reading time, even step by step is shown.
Interpolation of Scattered Data: Distance Matrices and Conditionally Positive Definite Functions
1,307 Citations1984Charles A. Micchelli
American Journal of PhysicsIntroduction to the Theory of Neural Computation
1,273 Citations1994John Hertz, Anders Krogh +2 more
This book is a detailed, logically-developed treatment that covers the theory and uses of collective computational networks, including associative memory, feed forward networks, and unsupervised learning.
Constructive ApproximationInterpolation of scattered data: Distance matrices and conditionally positive definite functions
1,213 Citations1986Charles A. Micchelli
NatureA network that learns to recognize three-dimensional objects
936 Citations1990Tomaso Poggio, Shimon Edelman
A scheme is developed, based on the theory of approximation of multivariate functions, that learns from a small set of perspective views a function mapping any viewpoint to a standard view, and a network equivalent to this scheme will 'recognize' the object on which it was trained from any viewpoint.
A Theory of Networks for Approximation and Learning
716 Citations1989Tomaso Poggio, Federico Girosi
Mathematics of ComputationMultivariate interpolation and conditionally positive definite functions. II
499 Citations1990W. R. Madych, S. A. Nelson
Neural ComputationReview of Neural Networks for Speech Recognition
480 Citations1989Richard P. Lippmann
Further work is necessary for large-vocabulary continuous-speech problems, to develop training algorithms that progressively build internal word models, and to develop compact VLSI neural net hardware.
The Annals of StatisticsA Simple Lemma on Greedy Approximation in Hilbert Space and Convergence Rates for Projection Pursuit Regression and Neural Network Training
474 Citations1992Lee Jones
A general convergence criterion for certain iterative sequences in Hilbert space is presented and results establish an 0(1/ F4n) nonsampling convergence rate for projection pursuit regression and neural network training.
Zeitschrift für angewandte Mathematik und PhysikMultivariate interpolation at arbitrary points made simple
410 Citations1979Jean Meinguet
SIAM Journal on Scientific and Statistical ComputingNumerical Procedures for Surface Fitting of Scattered Data by Radial Functions
400 Citations1986Nira Dyn, David I. W. Levin +1 more
The major theme of this work is the development of an iterative scheme for the construction of a smooth surface, presented by global basis functions, which approximates only the smooth components of a set of scattered noisy data.
Extensions of a Theory of Networks for Approximation and Learning: Dimensionality Reduction and Clustering
52 Citations1990Tomaso Poggio, Federico Girosi
The theory developed in Poggio and Girosi (1989) shows the equivalence between regularization and a class of three-layer networks that are called regularization networks or Hyper Basis Functions, which is extended by defining a general form of these networks with two sets of modifiable parameters.
Generalization Properties of Radial Basis Functions
31 Citations1990S. M. Botros, Christopher G. Atkeson
It is found that without a proper choice of a norm for the inputs, RBFs have poor generalization properties and a simple global scaling of the input variables greatly improves performance.
Neural Information Processing SystemsOriented Non-Radial Basis Functions for Image Coding and Analysis
22 Citations1990Avijit Saha, J Buhay Christian +2 more
Olympic oriented non-radial basis function networks (ONRBF) is introduced as a generalization of Radial Basis Function networks (RBF)- wherein the Euclidean distance metric in the exponent of the Gaussian is replaced by a more general polynomial.
A Nondeterministic Minimization Algorithm
20 Citations1990Bruno Caprile, Federico Girosi
A simple nondeterministic algorithm which is based on the idea of adaptive noise that proved to be particularly effective in the minimization of a class of multivariate functions associated with some recent extension of regularization theory by Poggio and Girosi (1990).
Biological CyberneticsOn random minimization of functions
16 Citations1991Giampietro Tecchiolli, Roberto Brunelli
Different variants of the basic algorithm are compared to a standard Conjugate Gradient minimization algorithm in the computation of the Rayleigh coefficient of a positive definite symmetric matrix.
Learning autonomous navigation abilities using radial basis functions networks
4 Citations2003Marco Aste, Bruno Caprile
A system that learns how to react to visual inputs in order to accomplish simple autonomous navigation tasks is presented, and experiments are reported which show how the system is able to attain a level of performances which is very close to the one displayed by its human trainers.