Radial Basis Functions, Multi-Variable Functional Interpolation and Adaptive Networks

By David S. Broomhead, D. Lowe. 1988

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Surrogate-Assisted Evolutionary Deep Learning Using an End-to-End Random Forest-Based Performance Predictor (2020, methodology): “using cheap approximated regression and classification models (like Gaussian process model [37], radial basis function network [38], etc.”
End-to-end Differentiable Proving (2017, methodology): “Otherwise, the vector representations of the two non-variable symbols are compared using a Radial Basis Function (RBF) kernel [30] where μ is a hyperparameter that we set to 1 √ 2 in our experiments.”
What are Extreme Learning Machines? Filling the Gap Between Frank Rosenblatt’s Dream and John von Neumann’s Puzzle (2015, background): “…draw their serious attention that our earlier work (2008) [4] has explicitly stated: “Several researchers [31], [32], [35], [62] (e.g., Baum (1988), Broomhead and Lowe (1988), Igelnik and Pao (1995), Ferrari and Stengel (2005)) have independently found that the input weights or centers a i do not…”
A review on extreme learning machine (2021, background): “RBFNN is a single hidden layer feedforward neural network based on function approximation proposed by Broomhead and Lowe [7] in the late 1980s.”
A survey of randomized algorithms for training neural networks (2016, background): “Another neural network architecture is radial basis function network (RBF network), which was brought to attention in the neural network community by [12, 52, 59], became popular because of its efficiency and ease of training.”
Local Learning Algorithms (1992, methodology): “To evaluate the output yGl&,al(x) of the complete system for an input pattern x, we merge these weighted averages according to the values of the X kernels on x. (3.4) This is a radial basis functions (RBF) network (Broomhead and Lowe 1988; Moody and Darken 1989).”
Transformation invariance in pattern recognition: Tangent distance and propagation (2000, background): “Output functions range from simply voting the labels associated with thek closest prototypes (K-Nearest Neighbors) to computing a score for each class as a linear combination of the distances to all the prototypes, using fixed (Parzen, 1962) or learned (Broomhead and Lowe, 1988) coefficients.”
Neural networks for the prediction and forecasting of water resource variables: a review of modelling issues and applications (2000, background): “Interested readers are referred to papers by Broomhead and Lowe (1988); Chng et al. (1996); Heiss and Kampl (1996).”
Reinforcement Learning: An Introduction (1998, methodology): “9.5.5 Function approximation using radial basis functions has received wide attention ever since being related to ANNs by Broomhead and Lowe (1988).”