Smooth function approximation using neural networks

By Silvia Ferrari, Robert F. Stengel. IEEE Transactions on Neural Networks, 2005

321 citations recorded by the source corpus.

How researchers see this paper

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

Hamiltonian Monte Carlo Acceleration Using Neural Network Surrogate functions (2015, background): “ion is usually quite slow and can be trapped at some local minimum since the cost function is nonlinear, and for most cases, non-convex. An alternative approach could be the algebraictraining methods [20, 21]. The key feature of algebraic training is that it decomposes the full optimization problem ”
Extreme learning machine: Theory and applications (2006, methodology): “Modular networks have also been suggested in several works [23,10,16,9,4], which partition the training samples into L subsets each learned by an SLFN separately.”
What are Extreme Learning Machines? Filling the Gap Between Frank Rosenblatt’s Dream and John von Neumann’s Puzzle (2015, background): “Ferrari and Stengel (2005) has been kindly referred in our work although it was even published later than ELM [24].)”