Nonlinearity creates linear independence
From MaRDI portal
Publication:1923888
DOI10.1007/BF02124743zbMath0855.92007MaRDI QIDQ1923888
Publication date: 9 February 1997
Published in: Advances in Computational Mathematics (Search for Journal in Brave)
Fourier transform; plane waves; scaling; linear independence; nonlinear mapping; activation function; shifting; complete linear independence; finite mapping; strict linear independence; structural uniqueness of neural networks
68T05: Learning and adaptive systems in artificial intelligence
92B20: Neural networks for/in biological studies, artificial life and related topics
Related Items
Activation Functions Defined on Higher-Dimensional Spaces for Approximation on Compact Sets with and without Scaling, Asymptotics of Reinforcement Learning with Neural Networks, Approximation by sums of ridge functions with fixed directions, Analysis and Design of Echo State Networks, Time discretization in the solution of parabolic PDEs with ANNs, Normalization effects on deep neural networks, Constructive approximate interpolation by neural networks, Hermite interpolation by neural networks, Interpolation by ridge polynomials and its application in neural networks, Neural network operators: constructive interpolation of multivariate functions, Normalization effects on shallow neural networks and related asymptotic expansions, Extreme learning machine collocation for the numerical solution of elliptic PDEs with sharp gradients, An associative memory readout for ESNs with applications to dynamical pattern recognition, Max-product neural network and quasi-interpolation operators activated by sigmoidal functions
Cites Work
- Multilayer feedforward networks are universal approximators
- Differentiable approximation by means of the Radon transformation and its applications to neural networks
- Approximation Capability of Layered Neural Networks with Sigmoid Units on Two Layers
- Learning representations by back-propagating errors
- A logical calculus of the ideas immanent in nervous activity
- Approximation by superpositions of a sigmoidal function
- Unnamed Item
- Unnamed Item
- Unnamed Item
