163 related articles for article (PubMed ID: 32946706)
1. 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]
2. Optimal approximation of piecewise smooth functions using deep ReLU neural networks.
Petersen P; Voigtlaender F
Neural Netw; 2018 Dec; 108():296-330. PubMed ID: 30245431
[TBL] [Abstract][Full Text] [Related]
3. Deep ReLU neural networks in high-dimensional approximation.
Dũng D; Nguyen VK
Neural Netw; 2021 Oct; 142():619-635. PubMed ID: 34392126
[TBL] [Abstract][Full Text] [Related]
4. Neural networks with ReLU powers need less depth.
Cabanilla KIM; Mohammad RZ; Lope JEC
Neural Netw; 2024 Apr; 172():106073. PubMed ID: 38159509
[TBL] [Abstract][Full Text] [Related]
5. Error bounds for approximations with deep ReLU networks.
Yarotsky D
Neural Netw; 2017 Oct; 94():103-114. PubMed ID: 28756334
[TBL] [Abstract][Full Text] [Related]
6. Approximation of smooth functionals using deep ReLU networks.
Song L; Liu Y; Fan J; Zhou DX
Neural Netw; 2023 Sep; 166():424-436. PubMed ID: 37549610
[TBL] [Abstract][Full Text] [Related]
7. Configuration of continuous piecewise-linear neural networks.
Wang S; Huang X; Junaid KM
IEEE Trans Neural Netw; 2008 Aug; 19(8):1431-45. PubMed ID: 18701372
[TBL] [Abstract][Full Text] [Related]
8. Deep Network With Approximation Error Being Reciprocal of Width to Power of Square Root of Depth.
Shen Z; Yang H; Zhang S
Neural Comput; 2021 Mar; 33(4):1005-1036. PubMed ID: 33513325
[TBL] [Abstract][Full Text] [Related]
9. Singular Values for ReLU Layers.
Dittmer S; King EJ; Maass P
IEEE Trans Neural Netw Learn Syst; 2020 Sep; 31(9):3594-3605. PubMed ID: 31714239
[TBL] [Abstract][Full Text] [Related]
10. On minimal representations of shallow ReLU networks.
Dereich S; Kassing S
Neural Netw; 2022 Apr; 148():121-128. PubMed ID: 35123261
[TBL] [Abstract][Full Text] [Related]
11. Simultaneous approximation of a smooth function and its derivatives by deep neural networks with piecewise-polynomial activations.
Belomestny D; Naumov A; Puchkin N; Samsonov S
Neural Netw; 2023 Apr; 161():242-253. PubMed ID: 36774863
[TBL] [Abstract][Full Text] [Related]
12. Nonlinear approximation via compositions.
Shen Z; Yang H; Zhang S
Neural Netw; 2019 Nov; 119():74-84. PubMed ID: 31401528
[TBL] [Abstract][Full Text] [Related]
13. Locally linear attributes of ReLU neural networks.
Sattelberg B; Cavalieri R; Kirby M; Peterson C; Beveridge R
Front Artif Intell; 2023; 6():1255192. PubMed ID: 38075385
[TBL] [Abstract][Full Text] [Related]
14. Universal approximation using incremental constructive feedforward networks with random hidden nodes.
Huang GB; Chen L; Siew CK
IEEE Trans Neural Netw; 2006 Jul; 17(4):879-892. PubMed ID: 16856652
[TBL] [Abstract][Full Text] [Related]
15. Neural-network approximation of piecewise continuous functions: application to friction compensation.
Selmic RR; Lewis FL
IEEE Trans Neural Netw; 2002; 13(3):745-51. PubMed ID: 18244470
[TBL] [Abstract][Full Text] [Related]
16. 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]
17. A Deep-Network Piecewise Linear Approximation Formula.
Zeng GL
IEEE Access; 2021; 9():120665-120674. PubMed ID: 34532202
[TBL] [Abstract][Full Text] [Related]
18. PWLU: Learning Specialized Activation Functions With the Piecewise Linear Unit.
Zhu Z; Zhou Y; Dong Y; Zhong Z
IEEE Trans Pattern Anal Mach Intell; 2023 Oct; 45(10):12269-12286. PubMed ID: 37314901
[TBL] [Abstract][Full Text] [Related]
19. A comparison of deep networks with ReLU activation function and linear spline-type methods.
Eckle K; Schmidt-Hieber J
Neural Netw; 2019 Feb; 110():232-242. PubMed ID: 30616095
[TBL] [Abstract][Full Text] [Related]
20. Integrating geometries of ReLU feedforward neural networks.
Liu Y; Caglar T; Peterson C; Kirby M
Front Big Data; 2023; 6():1274831. PubMed ID: 38033354
[TBL] [Abstract][Full Text] [Related]
[Next] [New Search]