Ill-Conditioning in Neural Network Training Problems

DOI10.1137/0914044zbMath0814.65070OpenAlexW1977923618MaRDI QIDQ4695054

George Cybenko, Randall Bramley, Sirpa Saarinen

Publication date: 18 June 1995

Published in: SIAM Journal on Scientific Computing (Search for Journal in Brave)

Full work available at URL: https://semanticscholar.org/paper/a62f69f42d0bade0980419741d4eea1fc7060c49

zbMATH Keywords

nonlinear parameter estimationill-conditioningexperimental resultsfeedforward neural networksneural network trainingoptimization methods

Mathematics Subject Classification ID

Numerical optimization and variational techniques (65K10) General systems theory (93A99)

Related Items (11)

Unnamed Item ⋮ Two Frameworks for Improving Gradient-Based Learning Algorithms ⋮ Variable projections neural network training ⋮ Nonlinear black-box modeling in system identification: A unified overview ⋮ Feedforward neural nets as discretization schemes for ODEs and DAEs ⋮ Second-order stagewise backpropagation for Hessian-matrix analyses and investigation of negative curvature ⋮ Error estimates and physics informed augmentation of neural networks for thermally coupled incompressible Navier Stokes equations ⋮ Overtraining, regularization and searching for a minimum, with application to neural networks ⋮ Establishing criteria to ensure successful feedforward artificial neural network modelling of mechanical systems ⋮ ADAPTIVE ALGORITHMS FOR NEURAL NETWORK SUPERVISED LEARNING: A DETERMINISTIC OPTIMIZATION APPROACH ⋮ Approximation properties of local bases assembled from neural network transfer functions

This page was built for publication: Ill-Conditioning in Neural Network Training Problems