Lower bounds for approximation by MLP neural networks
From MaRDI portal
Publication:1305902
DOI10.1016/S0925-2312(98)00111-8zbMath0931.68093WikidataQ127580329 ScholiaQ127580329MaRDI QIDQ1305902
Publication date: 22 September 1999
Published in: Neurocomputing (Search for Journal in Brave)
68T05: Learning and adaptive systems in artificial intelligence
Related Items
Unnamed Item, Unnamed Item, Deep Network With Approximation Error Being Reciprocal of Width to Power of Square Root of Depth, Optimal Approximation with Sparsely Connected Deep Neural Networks, Deep Network Approximation Characterized by Number of Neurons, Equivalence of approximation by convolutional neural networks and fully-connected networks, Deep neural networks for rotation-invariance approximation and learning, Approximation by sums of ridge functions with fixed directions, Computing the Approximation Error for Neural Networks with Weights Varying on Fixed Directions, A Single Hidden Layer Feedforward Network with Only One Neuron in the Hidden Layer Can Approximate Any Univariate Function, Neural network approximation: three hidden layers are enough, Approximation capabilities of neural networks on unbounded domains, Approximating smooth and sparse functions by deep neural networks: optimal approximation rates and saturation, The Kolmogorov-Arnold representation theorem revisited, Lower bounds for artificial neural network approximations: a proof that shallow neural networks fail to overcome the curse of dimensionality, Approximation error of single hidden layer neural networks with fixed weights, Approximation in shift-invariant spaces with deep ReLU neural networks, Linear and nonlinear approximation of spherical radial basis function networks, On the approximation by neural networks with bounded number of neurons in hidden layers, Approximation by neural networks with weights varying on a finite set of directions, Geometric properties of the ridge function manifold, Approximation by neural networks with a bounded number of nodes at each level, On lower bounds in radial basis approximation, Some problems in the theory of ridge functions, On best approximation of classes by radial functions, Essential rate for approximation by spherical neural networks, A neural network-based framework for financial model calibration, Model reduction and neural networks for parametric PDEs, Approximation rates for neural networks with encodable weights in smoothness spaces, On the representation by bivariate ridge functions, A theoretical analysis of deep neural networks and parametric PDEs, Approximation spaces of deep neural networks, SelectNet: self-paced learning for high-dimensional partial differential equations, An interval uncertainty analysis method for structural response bounds using feedforward neural network differentiation, On the approximation by single hidden layer feedforward neural networks with fixed weights, Optimal approximation of piecewise smooth functions using deep ReLU neural networks, Negative results for approximation using single layer and multilayer feedforward neural networks, Almost optimal estimates for approximation and learning by radial basis function networks, Limitations of shallow nets approximation, Approximation by neural networks and learning theory, Pseudo-dimension and entropy of manifolds formed by affine-invariant dictionary, Phase transitions in rate distortion theory and deep learning, A three layer neural network can represent any multivariate function, Complexity of Shallow Networks Representing Finite Mappings, The capability of approximation for neural networks interpolant on the sphere, The estimate for approximation error of spherical neural networks, Approximation by ridge functions and neural networks with a bounded number of neurons
