Refinement and Universal Approximation via Sparsely Connected ReLU Convolution Nets
Sign Up to like & getrecommendations! Published in 2020 at "IEEE Signal Processing Letters"
DOI: 10.1109/lsp.2020.3005051
Abstract: We construct a highly regular and simple structured class of sparsely connected convolutional neural networks with rectifier activations that provide universal function approximation in a coarse-to-fine manner with increasing number of layers. The networks are… read more here.
Keywords: convolution; sparsely connected; universal approximation; refinement universal ... See more keywords
Universal Approximation Power of Deep Residual Neural Networks Through the Lens of Control
Sign Up to like & getrecommendations! Published in 2023 at "IEEE Transactions on Automatic Control"
DOI: 10.1109/tac.2022.3190051
Abstract: In this article, we show that deep residual neural networks have the power of universal approximation by using, in an essential manner, the observation that these networks can be modeled as nonlinear control systems. We… read more here.
Keywords: neural networks; universal approximation; deep residual; control ... See more keywords
Universal Approximation of Fuzzy Relation Models by Semitensor Product
Sign Up to like & getrecommendations! Published in 2020 at "IEEE Transactions on Fuzzy Systems"
DOI: 10.1109/tfuzz.2019.2946512
Abstract: A universal approximation of multi-input multi-output (MIMO) fuzzy systems is proposed in this article based on a fuzzy relation matrix (FRM) method. The fuzzy reasoning operation in FRM is realized by the semitensor product (STP)… read more here.
Keywords: universal approximation; fuzzy systems; semitensor product; fuzzy relation ... See more keywords
Universal Approximation by Using the Correntropy Objective Function
Sign Up to like & getrecommendations! Published in 2018 at "IEEE Transactions on Neural Networks and Learning Systems"
DOI: 10.1109/tnnls.2017.2753725
Abstract: Several objective functions have been proposed in the literature to adjust the input parameters of a node in constructive networks. Furthermore, many researchers have focused on the universal approximation capability of the network based on… read more here.
Keywords: universal approximation; using correntropy; network; objective function ... See more keywords
Universal Approximation Capability of Broad Learning System and Its Structural Variations
Sign Up to like & getrecommendations! Published in 2019 at "IEEE Transactions on Neural Networks and Learning Systems"
DOI: 10.1109/tnnls.2018.2866622
Abstract: After a very fast and efficient discriminative broad learning system (BLS) that takes advantage of flatted structure and incremental learning has been developed, here, a mathematical proof of the universal approximation property of BLS is… read more here.
Keywords: learning system; universal approximation; learning; broad learning ... See more keywords
Universal Approximation Abilities of a Modular Differentiable Neural Network
Sign Up to like & getrecommendations! Published in 2024 at "IEEE Transactions on Neural Networks and Learning Systems"
DOI: 10.1109/tnnls.2024.3378697
Abstract: Approximation ability is one of the most important topics in the field of neural networks (NNs). Feedforward NNs, activated by rectified linear units and some of their specific smoothed versions, provide universal approximators to convex… read more here.
Keywords: modular differentiable; differentiable neural; abilities modular; approximation abilities ... See more keywords
Nonlinear function-on-scalar regression via functional universal approximation.
Sign Up to like & getrecommendations! Published in 2023 at "Biometrics"
DOI: 10.1111/biom.13838
Abstract: We consider general nonlinear Function-on-Scalar (FOS) regression models where the functional response depends on multiple scalar predictors in a general unknown nonlinear form. Existing methods either assume specific model forms (e.g., additive models) or directly… read more here.
Keywords: scalar predictors; regression; nonlinear function; universal approximation ... See more keywords
Prediction multimodal optical responses for ultrafast plasmonic based functional universal approximation theorem with exponential data efficiency.
Sign Up to like & getrecommendations! Published in 2025 at "Optics express"
DOI: 10.1364/oe.572501
Abstract: Machine learning offers efficient alternatives to traditional solvers for modeling nonlinear relationships between nanophotonic structures and their optical responses. However, neural network (NN)-based methods typically represent functional data as high-dimensional pointwise vectors without incorporating structural… read more here.
Keywords: based functional; data efficiency; optical responses; functional universal ... See more keywords