125 related articles for article (PubMed ID: 33267341)
21. Fast generalization error bound of deep learning without scale invariance of activation functions.
Terada Y; Hirose R
Neural Netw; 2020 Sep; 129():344-358. PubMed ID: 32593931
[TBL] [Abstract][Full Text] [Related]
22. Fast convergence rates of deep neural networks for classification.
Kim Y; Ohn I; Kim D
Neural Netw; 2021 Jun; 138():179-197. PubMed ID: 33676328
[TBL] [Abstract][Full Text] [Related]
23. Wide and deep neural networks achieve consistency for classification.
Radhakrishnan A; Belkin M; Uhler C
Proc Natl Acad Sci U S A; 2023 Apr; 120(14):e2208779120. PubMed ID: 36996114
[TBL] [Abstract][Full Text] [Related]
24. On decision regions of narrow deep neural networks.
Beise HP; Dias Da Cruz S; Schröder U
Neural Netw; 2021 Aug; 140():121-129. PubMed ID: 33756267
[TBL] [Abstract][Full Text] [Related]
25. Dimension independent bounds for general shallow networks.
Mhaskar HN
Neural Netw; 2020 Mar; 123():142-152. PubMed ID: 31869651
[TBL] [Abstract][Full Text] [Related]
26. Quantifying the generalization error in deep learning in terms of data distribution and neural network smoothness.
Jin P; Lu L; Tang Y; Karniadakis GE
Neural Netw; 2020 Oct; 130():85-99. PubMed ID: 32650153
[TBL] [Abstract][Full Text] [Related]
27. On the capacity of deep generative networks for approximating distributions.
Yang Y; Li Z; Wang Y
Neural Netw; 2022 Jan; 145():144-154. PubMed ID: 34749027
[TBL] [Abstract][Full Text] [Related]
28. Approximation properties of Gaussian-binary restricted Boltzmann machines and Gaussian-binary deep belief networks.
Gu L; Yang L; Zhou F
Neural Netw; 2022 Sep; 153():49-63. PubMed ID: 35700559
[TBL] [Abstract][Full Text] [Related]
29. Approximation of classifiers by deep perceptron networks.
Kůrková V; Sanguineti M
Neural Netw; 2023 Aug; 165():654-661. PubMed ID: 37364474
[TBL] [Abstract][Full Text] [Related]
30. Approximation rates for neural networks with general activation functions.
Siegel JW; Xu J
Neural Netw; 2020 Aug; 128():313-321. PubMed ID: 32470796
[TBL] [Abstract][Full Text] [Related]
31. Theory of deep convolutional neural networks III: Approximating radial functions.
Mao T; Shi Z; Zhou DX
Neural Netw; 2021 Dec; 144():778-790. PubMed ID: 34688019
[TBL] [Abstract][Full Text] [Related]
32. Theory of deep convolutional neural networks: Downsampling.
Zhou DX
Neural Netw; 2020 Apr; 124():319-327. PubMed ID: 32036229
[TBL] [Abstract][Full Text] [Related]
33. Error bounds for deep ReLU networks using the Kolmogorov-Arnold superposition theorem.
Montanelli H; Yang H
Neural Netw; 2020 Sep; 129():1-6. PubMed ID: 32473577
[TBL] [Abstract][Full Text] [Related]
34. ReLU Networks Are Universal Approximators via Piecewise Linear or Constant Functions.
Huang C
Neural Comput; 2020 Nov; 32(11):2249-2278. PubMed ID: 32946706
[TBL] [Abstract][Full Text] [Related]
35. On PDE Characterization of Smooth Hierarchical Functions Computed by Neural Networks.
Filom K; Farhoodi R; Kording KP
Neural Comput; 2021 Nov; 33(12):3204-3263. PubMed ID: 34710899
[TBL] [Abstract][Full Text] [Related]
36. On the optimality of neural-network approximation using incremental algorithms.
Meir R; Maiorov VE
IEEE Trans Neural Netw; 2000; 11(2):323-37. PubMed ID: 18249764
[TBL] [Abstract][Full Text] [Related]
37. Analytic Function Approximation by Path-Norm-Regularized Deep Neural Networks.
Beknazaryan A
Entropy (Basel); 2022 Aug; 24(8):. PubMed ID: 36010799
[TBL] [Abstract][Full Text] [Related]
38. The Kolmogorov-Arnold representation theorem revisited.
Schmidt-Hieber J
Neural Netw; 2021 May; 137():119-126. PubMed ID: 33592434
[TBL] [Abstract][Full Text] [Related]
39. A neural network of smooth hinge functions.
Wang S; Huang X; Yam Y
IEEE Trans Neural Netw; 2010 Sep; 21(9):1381-95. PubMed ID: 20682471
[TBL] [Abstract][Full Text] [Related]
40. Integral representations of shallow neural network with rectified power unit activation function.
Abdeljawad A; Grohs P
Neural Netw; 2022 Nov; 155():536-550. PubMed ID: 36166980
[TBL] [Abstract][Full Text] [Related]
[Previous] [Next] [New Search]