Close Search Advanced
Journals
Resources
About Us
Open Access

ReLU Deep Neural Networks and Linear Finite Elements

ReLU Deep Neural Networks and Linear Finite Elements
Preview
Add to basket

Year:    2020

Author:    Juncai He, Lin Li, Jinchao Xu, Chunyue Zheng

Journal of Computational Mathematics, Vol. 38 (2020), Iss. 3 : pp. 502–527

Abstract

In this paper, we investigate the relationship between deep neural networks (DNN) with rectified linear unit (ReLU) function as the activation function and continuous piecewise linear (CPWL) functions, especially CPWL functions from the simplicial linear finite element method (FEM). We first consider the special case of FEM. By exploring the DNN representation of its nodal basis functions, we present a ReLU DNN representation of CPWL in FEM. We theoretically establish that at least $2$ hidden layers are needed in a ReLU DNN to represent any linear finite element functions in $\Omega \subseteq \mathbb{R}^d$ when $d\ge2$.  Consequently, for $d=2,3$ which are often encountered in scientific and engineering computing, the minimal number of two hidden layers are necessary and sufficient for any CPWL function to be represented by a ReLU DNN. Then we include a detailed account on how a general CPWL in $\mathbb R^d$ can be represented by a ReLU DNN with at most $\lceil\log_2(d+1)\rceil$ hidden layers and we also give an estimation of the number of neurons in DNN that are needed in such a representation.  Furthermore, using the relationship between DNN and FEM, we theoretically argue that a special class of DNN models with low bit-width are still expected to have an adequate representation power in applications.  Finally, as a proof of concept, we present some numerical results for using ReLU DNNs to solve a two-point boundary problem to demonstrate the potential of applying DNN for numerical solution of partial differential equations.


Submit Article

You do not have full access to this article.

Already a Subscriber? Sign in as an individual or via your institution

Journal Article Details

Publisher Name:    Global Science Press

Language:    English

DOI:    https://doi.org/10.4208/jcm.1901-m2018-0160

Journal of Computational Mathematics, Vol. 38 (2020), Iss. 3 : pp. 502–527

Published online:    2020-01

AMS Subject Headings:   

Copyright:    COPYRIGHT: © Global Science Press

Pages:    26

Keywords:    Finite element method deep neural network piecewise linear function.

Author Details

Juncai He

Lin Li

Jinchao Xu

Chunyue Zheng

  1. Computational Sciences and Artificial Intelligence in Industry

    Artificial Intelligence and Computational Science

    Neittaanmäki, Pekka | Repin, Sergey

    2022

    https://doi.org/10.1007/978-3-030-70787-3_3 [Citations: 1]

  2. Simultaneous neural network approximation for smooth functions

    Hon, Sean | Yang, Haizhao

    Neural Networks, Vol. 154 (2022), Iss. P.152

    https://doi.org/10.1016/j.neunet.2022.06.040 [Citations: 7]

  3. Learning quantized neural nets by coarse gradient method for nonlinear classification

    Long, Ziang | Yin, Penghang | Xin, Jack

    Research in the Mathematical Sciences, Vol. 8 (2021), Iss. 3

    https://doi.org/10.1007/s40687-021-00281-4 [Citations: 0]
  4. Machine Learning in Modeling and Simulation

    Physics-Informed Neural Networks: Theory and Applications

    Anitescu, Cosmin | İsmail Ateş, Burak | Rabczuk, Timon

    2023

    https://doi.org/10.1007/978-3-031-36644-4_5 [Citations: 1]

  5. MIM: A deep mixed residual method for solving high-order partial differential equations

    Lyu, Liyao | Zhang, Zhen | Chen, Minxin | Chen, Jingrun

    Journal of Computational Physics, Vol. 452 (2022), Iss. P.110930

    https://doi.org/10.1016/j.jcp.2021.110930 [Citations: 39]

  6. Integrating handcrafted features with deep convolutional neural network and BWOA optimization for improved postmortem iris recognition system

    Kaur, Bhupinder | Saini, Surender Singh

    Soft Computing, Vol. (2024), Iss.

    https://doi.org/10.1007/s00500-024-10316-x [Citations: 0]

  7. Randomized neural network with Petrov–Galerkin methods for solving linear and nonlinear partial differential equations

    Shang, Yong | Wang, Fei | Sun, Jingbo

    Communications in Nonlinear Science and Numerical Simulation, Vol. 127 (2023), Iss. P.107518

    https://doi.org/10.1016/j.cnsns.2023.107518 [Citations: 9]

  8. Distributed learning machines for solving forward and inverse problems in partial differential equations

    Dwivedi, Vikas | Parashar, Nishant | Srinivasan, Balaji

    Neurocomputing, Vol. 420 (2021), Iss. P.299

    https://doi.org/10.1016/j.neucom.2020.09.006 [Citations: 59]

  9. Improved Deep Q-Network for User-Side Battery Energy Storage Charging and Discharging Strategy in Industrial Parks

    Chen, Shuai | Jiang, Chengpeng | Li, Jinglin | Xiang, Jinwei | Xiao, Wendong

    Entropy, Vol. 23 (2021), Iss. 10 P.1311

    https://doi.org/10.3390/e23101311 [Citations: 9]

  10. Can neural networks learn finite elements?

    Novo, Julia | Terrés, Eduardo

    Journal of Computational and Applied Mathematics, Vol. 453 (2025), Iss. P.116168

    https://doi.org/10.1016/j.cam.2024.116168 [Citations: 0]

  11. A new integrated framework to fault detection and diagnosis of air handling unit: Emphasizing the impact of symptoms

    Hwan Cha, Jae | Kyu Park, Jun | Hyeon Chi, Chang | Hun Yeon, Sang | Ho Kim, Chul | Woo Moon, Jin | Ho Lee, Kwang

    Energy and Buildings, Vol. 319 (2024), Iss. P.114474

    https://doi.org/10.1016/j.enbuild.2024.114474 [Citations: 1]
  12. Proceedings of Trends in Electronics and Health Informatics

    Flexible Systolic Hardware Architecture for Computing a Custom Lightweight CNN in CT Images Processing for Automated COVID-19 Diagnosis

    Aguirre-Alvarez, Paulo Aarón | Diaz-Carmona, Javier | Arredondo-Velázquez, Moisés

    2023

    https://doi.org/10.1007/978-981-99-1916-1_2 [Citations: 1]

  13. Data-driven physics-informed interpolation evolution combining historical-predicted knowledge for remaining oil distribution prediction

    Song, Hongqing | Zhu, Jingwei | Wei, Chenji | Wang, Jiulong | Du, Shuyi | Xie, Chiyu

    Journal of Petroleum Science and Engineering, Vol. 217 (2022), Iss. P.110795

    https://doi.org/10.1016/j.petrol.2022.110795 [Citations: 10]

  14. On the approximation of bi-Lipschitz maps by invertible neural networks

    Jin, Bangti | Zhou, Zehui | Zou, Jun

    Neural Networks, Vol. 174 (2024), Iss. P.106214

    https://doi.org/10.1016/j.neunet.2024.106214 [Citations: 0]

  15. An interpretable machine learning approach to study the relationship beetwen retrognathia and skull anatomy

    Makaremi, Masrour | Vafaei Sadr, Alireza | Marcy, Benoit | Chraibi Kaadoud, Ikram | Mohammad-Djafari, Ali | Sadoun, Salomé | De Brondeau, François | N’kaoua, Bernard

    Scientific Reports, Vol. 13 (2023), Iss. 1

    https://doi.org/10.1038/s41598-023-45314-w [Citations: 0]

  16. Physically motivated structuring and optimization of neural networks for multi-physics modelling of solid oxide fuel cells

    Rauh, Andreas | Kersten, Julia | Frenkel, Wiebke | Kruse, Niklas | Schmidt, Tom

    Mathematical and Computer Modelling of Dynamical Systems, Vol. 27 (2021), Iss. 1 P.586

    https://doi.org/10.1080/13873954.2021.1990966 [Citations: 5]

  17. Solving Parametric Partial Differential Equations with Deep Rectified Quadratic Unit Neural Networks

    Lei, Zhen | Shi, Lei | Zeng, Chenyu

    Journal of Scientific Computing, Vol. 93 (2022), Iss. 3

    https://doi.org/10.1007/s10915-022-02015-2 [Citations: 5]

  18. Demonstration of object location, classification, and characterization by developed deep learning dust ablation trail analysis code package using plasma jets

    Liang, Chen | Ma, Zhuang | Sun, Zhen | Zhang, Xiaoman | You, Xin | Liu, Zhuang | Zuo, Guizhong | Hu, Jiansheng | Feng, Yan

    Review of Scientific Instruments, Vol. 94 (2023), Iss. 2

    https://doi.org/10.1063/5.0123614 [Citations: 1]

  19. On the use of kolmogorov–arnold networks for adapting wind numerical weather forecasts with explainability and interpretability: application to madeira international airport

    Alves, Décio | Mendonça, Fábio | Mostafa, Sheikh Shanawaz | Morgado-Dias, Fernando

    Environmental Research Communications, Vol. 6 (2024), Iss. 10 P.105008

    https://doi.org/10.1088/2515-7620/ad810f [Citations: 0]

  20. A deep neural network approach for parameterized PDEs and Bayesian inverse problems

    Antil, Harbir | Elman, Howard C | Onwunta, Akwum | Verma, Deepanshu

    Machine Learning: Science and Technology, Vol. 4 (2023), Iss. 3 P.035015

    https://doi.org/10.1088/2632-2153/ace67c [Citations: 3]

  21. Inclined Curved Crack Composite Beam: Experimental and Computational Analysis with Recycled Aluminum Composite Materials and Comparison with an Artificial Neural Network

    Ravichandran, Ashok | Mohanty, Prases K | Asiri, Abdullah Naser M | Islam, Saiful

    ACS Omega, Vol. 9 (2024), Iss. 4 P.4395

    https://doi.org/10.1021/acsomega.3c04535 [Citations: 0]

  22. Approximation rates of DeepONets for learning operators arising from advection–diffusion equations

    Deng, Beichuan | Shin, Yeonjong | Lu, Lu | Zhang, Zhongqiang | Karniadakis, George Em

    Neural Networks, Vol. 153 (2022), Iss. P.411

    https://doi.org/10.1016/j.neunet.2022.06.019 [Citations: 36]

  23. Power series expansion neural network

    Chen, Qipin | Hao, Wenrui | He, Juncai

    Journal of Computational Science, Vol. 59 (2022), Iss. P.101552

    https://doi.org/10.1016/j.jocs.2021.101552 [Citations: 4]

  24. A Deep-Network Piecewise Linear Approximation Formula

    Zeng, Gengsheng L.

    IEEE Access, Vol. 9 (2021), Iss. P.120665

    https://doi.org/10.1109/ACCESS.2021.3109173 [Citations: 3]

  25. Neural network approximation

    DeVore, Ronald | Hanin, Boris | Petrova, Guergana

    Acta Numerica, Vol. 30 (2021), Iss. P.327

    https://doi.org/10.1017/S0962492921000052 [Citations: 86]

  26. Machine Learning Architectures for Price Formation Models

    Gomes, Diogo | Gutierrez, Julian | Laurière, Mathieu

    Applied Mathematics & Optimization, Vol. 88 (2023), Iss. 1

    https://doi.org/10.1007/s00245-023-10002-8 [Citations: 2]

  27. A finite-element-informed neural network for parametric simulation in structural mechanics

    Le-Duc, Thang | Nguyen-Xuan, H. | Lee, Jaehong

    Finite Elements in Analysis and Design, Vol. 217 (2023), Iss. P.103904

    https://doi.org/10.1016/j.finel.2022.103904 [Citations: 11]

  28. Approximation properties of deep ReLU CNNs

    He, Juncai | Li, Lin | Xu, Jinchao

    Research in the Mathematical Sciences, Vol. 9 (2022), Iss. 3

    https://doi.org/10.1007/s40687-022-00336-0 [Citations: 10]

  29. Numerical solving for generalized Black-Scholes-Merton model with neural finite element method

    Chen, Yinghao | Wei, Lei | Cao, Shen | Liu, Fan | Yang, Yunlei | Cheng, Yangjin

    Digital Signal Processing, Vol. 131 (2022), Iss. P.103757

    https://doi.org/10.1016/j.dsp.2022.103757 [Citations: 7]

  30. An Ensemble-Based Model for Specific Humidity Retrieval from Landsat-8 Satellite Data for South Korea

    Choi, Sungwon | Seong, Noh-Hun | Jung, Daeseong | Sim, Suyoung | Woo, Jongho | Kim, Nayeon | Park, Sungwoo | Han, Kyung-soo

    Atmosphere, Vol. 15 (2024), Iss. 2 P.218

    https://doi.org/10.3390/atmos15020218 [Citations: 0]

  31. DeepFEM: A Novel Element-Based Deep Learning Approach for Solving Nonlinear Partial Differential Equations in Computational Solid Mechanics

    Dong, Yijia | Liu, Tao | Li, Zhimin | Qiao, Pizhong

    Journal of Engineering Mechanics, Vol. 149 (2023), Iss. 2

    https://doi.org/10.1061/JENMDT.EMENG-6643 [Citations: 5]

  32. Physics-informed graph neural network emulation of soft-tissue mechanics

    Dalton, David | Husmeier, Dirk | Gao, Hao

    Computer Methods in Applied Mechanics and Engineering, Vol. 417 (2023), Iss. P.116351

    https://doi.org/10.1016/j.cma.2023.116351 [Citations: 13]

  33. Deep learning-assisted inverse design of nanoparticle-embedded radiative coolers

    Kim, Min Ju | Kim, June Tae | Hong, Mi Jin | Park, Sang Wook | Lee, Gil Ju

    Optics Express, Vol. 32 (2024), Iss. 9 P.16235

    https://doi.org/10.1364/OE.518164 [Citations: 2]

  34. Breast Cancer Detection Using Deep Learning: An Investigation Using the DDSM Dataset and a Customized AlexNet and Support Vector Machine

    Ahmad, Jawad | Akram, Sheeraz | Jaffar, Arfan | Rashid, Muhammad | Bhatti, Sohail Masood

    IEEE Access, Vol. 11 (2023), Iss. P.108386

    https://doi.org/10.1109/ACCESS.2023.3311892 [Citations: 8]

  35. Spatial weighting — An effective incorporation of geological expertise into deep learning models

    Wang, Wenlei | Zhao, Chenyi | Wu, Yixiao

    Geochemistry, Vol. (2024), Iss. P.126212

    https://doi.org/10.1016/j.chemer.2024.126212 [Citations: 0]

  36. Adaptive two-layer ReLU neural network: I. Best least-squares approximation

    Liu, Min | Cai, Zhiqiang | Chen, Jingshuang

    Computers & Mathematics with Applications, Vol. 113 (2022), Iss. P.34

    https://doi.org/10.1016/j.camwa.2022.03.005 [Citations: 14]

  37. Interval universal approximation for neural networks

    Wang, Zi | Albarghouthi, Aws | Prakriya, Gautam | Jha, Somesh

    Proceedings of the ACM on Programming Languages, Vol. 6 (2022), Iss. POPL P.1

    https://doi.org/10.1145/3498675 [Citations: 7]

  38. Graph Neural Network-Based Node Deployment for Throughput Enhancement

    Yang, Yifei | Zou, Dongmian | He, Xiaofan

    IEEE Transactions on Neural Networks and Learning Systems, Vol. 35 (2024), Iss. 10 P.14810

    https://doi.org/10.1109/TNNLS.2023.3281643 [Citations: 2]

  39. A unified and constructive framework for the universality of neural networks

    Bui-Thanh, Tan

    IMA Journal of Applied Mathematics, Vol. 89 (2024), Iss. 1 P.197

    https://doi.org/10.1093/imamat/hxad032 [Citations: 0]

  40. Adaptive quadratures for nonlinear approximation of low-dimensional PDEs using smooth neural networks

    Magueresse, Alexandre | Badia, Santiago

    Computers & Mathematics with Applications, Vol. 162 (2024), Iss. P.1

    https://doi.org/10.1016/j.camwa.2024.02.041 [Citations: 0]

  41. DeepParticle: Learning invariant measure by a deep neural network minimizing Wasserstein distance on data generated from an interacting particle method

    Wang, Zhongjian | Xin, Jack | Zhang, Zhiwen

    Journal of Computational Physics, Vol. 464 (2022), Iss. P.111309

    https://doi.org/10.1016/j.jcp.2022.111309 [Citations: 4]

  42. SPINN: Sparse, Physics-based, and partially Interpretable Neural Networks for PDEs

    Ramabathiran, Amuthan A. | Ramachandran, Prabhu

    Journal of Computational Physics, Vol. 445 (2021), Iss. P.110600

    https://doi.org/10.1016/j.jcp.2021.110600 [Citations: 43]

  43. Galerkin Neural Networks: A Framework for Approximating Variational Equations with Error Control

    Ainsworth, Mark | Dong, Justin

    SIAM Journal on Scientific Computing, Vol. 43 (2021), Iss. 4 P.A2474

    https://doi.org/10.1137/20M1366587 [Citations: 17]

  44. Solving nonconvex energy minimization problems in martensitic phase transitions with a mesh-free deep learning approach

    Chen, Xiaoli | Rosakis, Phoebus | Wu, Zhizhang | Zhang, Zhiwen

    Computer Methods in Applied Mechanics and Engineering, Vol. 416 (2023), Iss. P.116384

    https://doi.org/10.1016/j.cma.2023.116384 [Citations: 0]

  45. Adaptive two-layer ReLU neural network: II. Ritz approximation to elliptic PDEs

    Liu, Min | Cai, Zhiqiang

    Computers & Mathematics with Applications, Vol. 113 (2022), Iss. P.103

    https://doi.org/10.1016/j.camwa.2022.03.010 [Citations: 7]

  46. DeepParticle: Learning Invariant Measure by a Deep Neural Network Minimizing Wasserstein Distance on Data Generated from an Interacting Particle Method

    Wang, Zhongjian | Xin, Jack | Zhang, Zhiwen

    SSRN Electronic Journal , Vol. (2021), Iss.

    https://doi.org/10.2139/ssrn.3983884 [Citations: 0]

  47. Machine learning algorithms for diagnosing of knee osteoarthritis using radiographs

    Abdalla, Hussein Najeeb | Gharghan, Sadik Kamel | Atee, Hayfaa Abdulzahra

    THE FIFTH SCIENTIFIC CONFERENCE FOR ELECTRICAL ENGINEERING TECHNIQUES RESEARCH (EETR2024), (2024), P.020036

    https://doi.org/10.1063/5.0236197 [Citations: 0]

  48. Double-net DDPG with the Optimal Action Selection Mechanism

    Li, Dazi | Dong, Caibo

    2022 IEEE 11th Data Driven Control and Learning Systems Conference (DDCLS), (2022), P.1166

    https://doi.org/10.1109/DDCLS55054.2022.9858412 [Citations: 1]

  49. Deep Learning Predicts Ar/O2 Plasma in Inductively Coupled Plasma Discharge

    Lee, Sang-Bin | Kim, Ji-Hoon | Kim, Gwan | Park, Jun-Woo | Chae, Byung-Kwan | Choe, Hee-Hwan

    Applied Science and Convergence Technology, Vol. 32 (2023), Iss. 5 P.122

    https://doi.org/10.5757/ASCT.2023.32.5.122 [Citations: 1]

  50. Exponential ReLU Neural Network Approximation Rates for Point and Edge Singularities

    Marcati, Carlo | Opschoor, Joost A. A. | Petersen, Philipp C. | Schwab, Christoph

    Foundations of Computational Mathematics, Vol. 23 (2023), Iss. 3 P.1043

    https://doi.org/10.1007/s10208-022-09565-9 [Citations: 10]

  51. A machine learning approach to portfolio pricing and risk management for high‐dimensional problems

    Fernandez‐Arjona, Lucio | Filipović, Damir

    Mathematical Finance, Vol. 32 (2022), Iss. 4 P.982

    https://doi.org/10.1111/mafi.12358 [Citations: 8]

  52. Polynomial-Spline Networks with Exact Integrals and Convergence Rates

    Actor, Jonas A. | Huang, Andy | Trask, Nat

    2022 IEEE Symposium Series on Computational Intelligence (SSCI), (2022), P.1156

    https://doi.org/10.1109/SSCI51031.2022.10022123 [Citations: 0]

  53. Deep learning or interpolation for inverse modelling of heat and fluid flow problems?

    Löhner, Rainald | Antil, Harbir | Tamaddon-Jahromi, Hamid | Chakshu, Neeraj Kavan | Nithiarasu, Perumal

    International Journal of Numerical Methods for Heat & Fluid Flow, Vol. 31 (2021), Iss. 9 P.3036

    https://doi.org/10.1108/HFF-11-2020-0684 [Citations: 13]

  54. A deep First-Order System Least Squares method for solving elliptic PDEs

    Bersetche, Francisco M. | Borthagaray, Juan Pablo

    Computers & Mathematics with Applications, Vol. 129 (2023), Iss. P.136

    https://doi.org/10.1016/j.camwa.2022.11.014 [Citations: 5]

  55. Stable parameterization of continuous and piecewise-linear functions

    Goujon, Alexis | Campos, Joaquim | Unser, Michael

    Applied and Computational Harmonic Analysis, Vol. 67 (2023), Iss. P.101581

    https://doi.org/10.1016/j.acha.2023.101581 [Citations: 4]

  56. A Method for All-Weather Unstructured Road Drivable Area Detection Based on Improved Lite-Mobilenetv2

    Wang, Qingyu | Lyu, Chenchen | Li, Yanyan

    Applied Sciences, Vol. 14 (2024), Iss. 17 P.8019

    https://doi.org/10.3390/app14178019 [Citations: 0]

  57. Physics-informed machine learning

    Karniadakis, George Em | Kevrekidis, Ioannis G. | Lu, Lu | Perdikaris, Paris | Wang, Sifan | Yang, Liu

    Nature Reviews Physics, Vol. 3 (2021), Iss. 6 P.422

    https://doi.org/10.1038/s42254-021-00314-5 [Citations: 2689]

  58. Estimating adsorption isotherm parameters in chromatography via a virtual injection promoting double feed-forward neural network

    Xu, Chen | Zhang, Ye

    Journal of Inverse and Ill-posed Problems, Vol. 0 (2022), Iss. 0

    https://doi.org/10.1515/jiip-2020-0121 [Citations: 3]

  59. Gauss Newton Method for Solving Variational Problems of PDEs with Neural Network Discretizaitons

    Hao, Wenrui | Hong, Qingguo | Jin, Xianlin

    Journal of Scientific Computing, Vol. 100 (2024), Iss. 1

    https://doi.org/10.1007/s10915-024-02535-z [Citations: 0]

  60. Data-driven simulation in fluids animation: A survey

    Chen, Qian | Wang, Yue | Wang, Hui | Yang, Xubo

    Virtual Reality & Intelligent Hardware, Vol. 3 (2021), Iss. 2 P.87

    https://doi.org/10.1016/j.vrih.2021.02.002 [Citations: 10]

  61. Forecasting care seekers satisfaction with telemedicine using machine learning and structural equation modeling

    Zobair, Khondker Mohammad | Sanzogni, Louis | Houghton, Luke | Islam, Md. Zahidul | Delcea, Camelia

    PLOS ONE, Vol. 16 (2021), Iss. 9 P.e0257300

    https://doi.org/10.1371/journal.pone.0257300 [Citations: 26]

  62. Data-Driven Natural Gas Compressor Models for Gas Transport Network Optimization

    Marfatia, Zaid | Li, Xiang

    Digital Chemical Engineering, Vol. 3 (2022), Iss. P.100030

    https://doi.org/10.1016/j.dche.2022.100030 [Citations: 1]

  63. Image Segmentation Method with Joint Loss Optimization for Apple Picking

    Zhihao, Xiong | Pan, Hang | Zhao, Yongjia | Chen, Jinlong | Yang, Minghao

    2024 5th International Conference on Computer Engineering and Application (ICCEA), (2024), P.901

    https://doi.org/10.1109/ICCEA62105.2024.10604066 [Citations: 0]

  64. ReLU deep neural networks from the hierarchical basis perspective

    He, Juncai | Li, Lin | Xu, Jinchao

    Computers & Mathematics with Applications, Vol. 120 (2022), Iss. P.105

    https://doi.org/10.1016/j.camwa.2022.06.006 [Citations: 19]

  65. Locally refined quad meshing for linear elasticity problems based on convolutional neural networks

    Chan, Chiu Ling | Scholz, Felix | Takacs, Thomas

    Engineering with Computers, Vol. 38 (2022), Iss. 5 P.4631

    https://doi.org/10.1007/s00366-022-01677-8 [Citations: 5]

  66. ReLU Neural Network Galerkin BEM

    Aylwin, Rubén | Henríquez, Fernando | Schwab, Christoph

    Journal of Scientific Computing, Vol. 95 (2023), Iss. 2

    https://doi.org/10.1007/s10915-023-02120-w [Citations: 2]

  67. Deep learning algorithms for solving differential equations: a survey

    Kumar, Harender | Yadav, Neha

    Journal of Experimental & Theoretical Artificial Intelligence, Vol. (2023), Iss. P.1

    https://doi.org/10.1080/0952813X.2023.2242356 [Citations: 0]

  68. Towards Lower Bounds on the Depth of ReLU Neural Networks

    Hertrich, Christoph | Basu, Amitabh | Di Summa, Marco | Skutella, Martin

    SIAM Journal on Discrete Mathematics, Vol. 37 (2023), Iss. 2 P.997

    https://doi.org/10.1137/22M1489332 [Citations: 2]

  69. Combining Deep Neural Network and PLS-SEM to Predict Patients’ Continuity with Telemedicine

    Zobair, Khondker Mohammad | Sanzogni, Louis | Houghton, Luke | Islam, Md. Zahidul

    International Journal of Information Technology & Decision Making, Vol. 21 (2022), Iss. 05 P.1555

    https://doi.org/10.1142/S0219622022500249 [Citations: 3]

  70. Piecewise linear functions representable with infinite width shallow ReLU neural networks

    McCarty, Sarah

    Proceedings of the American Mathematical Society, Series B, Vol. 10 (2023), Iss. 27 P.296

    https://doi.org/10.1090/bproc/186 [Citations: 0]

  71. A convergent Deep Learning algorithm for approximation of polynomials

    Després, Bruno

    Comptes Rendus. Mathématique, Vol. 361 (2023), Iss. G6 P.1029

    https://doi.org/10.5802/crmath.462 [Citations: 0]

  72. Approximation of Nonlinear Functionals Using Deep ReLU Networks

    Song, Linhao | Fan, Jun | Chen, Di-Rong | Zhou, Ding-Xuan

    Journal of Fourier Analysis and Applications, Vol. 29 (2023), Iss. 4

    https://doi.org/10.1007/s00041-023-10027-1 [Citations: 4]

  73. AMLNet: Attention Multibranch Loss CNN Models for Fine-Grained Vehicle Recognition

    Lu, Hongchun | Han, Min | Wang, Chaoqing | Cheng, Junlong

    IEEE Transactions on Vehicular Technology, Vol. 73 (2024), Iss. 1 P.375

    https://doi.org/10.1109/TVT.2023.3309707 [Citations: 0]