Model selection in neural networks: some difficulties

DOI10.1016/j.ejor.2004.05.026zbMath1085.90006OpenAlexW2012814015MaRDI QIDQ2572255

Yanyan Li

Publication date: 16 November 2005

Published in: European Journal of Operational Research (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.ejor.2004.05.026

zbMATH Keywords

Neural NetworksBackpropagationPolytopeHidden layersNetwork weights

Mathematics Subject Classification ID

Deterministic network models in operations research (90B10) Neural networks for/in biological studies, artificial life and related topics (92B20)

Related Items

Radial basis function neural network model for mean velocity and vorticity of capillary flow ⋮ Neural networks and seasonality: Some technical considerations ⋮ Parameter redundancy in neural networks: an application of Chebyshev polynomials ⋮ Neural network metamodeling for cycle time-throughput profiles in manufacturing ⋮ Wavelet neural networks: a practical guide

Cites Work

• Unnamed Item
• Unnamed Item
• Testing for neglected nonlinearity in time series models. A comparison of neural network methods and alternative tests
• Neural networks and nonlinear statistical methods: An application to the modelling of price-quality relationships
• Universal approximation bounds for superpositions of a sigmoidal function
• Pruning neural networks by minimization of the estimated variance
• Some Asymptotic Results for Learning in Single Hidden-Layer Feedforward Network Models
• A Stochastic Approximation Method
• Approximation by superpositions of a sigmoidal function

This page was built for publication: Model selection in neural networks: some difficulties