Minimization of Error Functionals over Perceptron Networks
From MaRDI portal
Publication:3539962
DOI10.1162/neco.2008.20.1.252zbMath1149.92007WikidataQ51899605 ScholiaQ51899605MaRDI QIDQ3539962
Publication date: 19 November 2008
Published in: Neural Computation (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.1162/neco.2008.20.1.252
62P10: Applications of statistics to biology and medical sciences; meta analysis
68T05: Learning and adaptive systems in artificial intelligence
92C20: Neural biology
65K99: Numerical methods for mathematical programming, optimization and variational techniques
Related Items
Lower bounds for artificial neural network approximations: a proof that shallow neural networks fail to overcome the curse of dimensionality, Complexity of Gaussian-radial-basis networks approximating smooth functions, Complexity estimates based on integral transforms induced by computational units, Simultaneous Approximations of Polynomials and Derivatives and Their Applications to Neural Networks
Cites Work
- A simple lemma on greedy approximation in Hilbert space and convergence rates for projection pursuit regression and neural network training
- Approximation by superposition of sigmoidal and radial basis functions
- Uniform approximation by neural networks
- On the bent Boolean functions that are symmetric
- Best approximation by linear combinations of characteristic functions of half-spaces.
- A better approximation for balls
- Geometry and topology of continuous best and near best approximations
- Multilayer feedforward networks are universal approximators
- Random approximants and neural networks
- Quasiorthogonal dimension of Euclidean spaces
- A Sobolev-type upper bound for rates of approximation by linear combinations of Heaviside plane waves
- On the mathematical foundations of learning
- Universal approximation bounds for superpositions of a sigmoidal function
- Approximation by superpositions of a sigmoidal function
