Neural network with unbounded activation functions is universal approximator

ImageNet classification with deep convolutional neural networks

Krizhevsky, A., Sutskever, I., & Hinton, G. E. (2017) · Communications of the ACM · doi:10.1145/3065386 · Cited by 112,155

Singular Integrals and Differentiability Properties of Functions.

Stein, E. M. (1971) · Cited by 10,183

Untitled work

(2011) · Cited by 6,993

Functional Analysis, Sobolev Spaces and Partial Differential Equations

Brézis, H. (2010) · Springer eBooks · doi:10.1007/978-0-387-70914-7 · Cited by 5,821

On the approximate realization of continuous mappings by neural networks

Funahashi, K.-I. (1989) · Neural Networks · doi:10.1016/0893-6080(89)90003-8 · Cited by 4,206

Universal approximation bounds for superpositions of a sigmoidal function

Barron, A. R. (1993) · IEEE Transactions on Information Theory · doi:10.1109/18.256500 · Cited by 2,935

The Fourier reconstruction of a head section

Shepp, L. A., & Logan, B. F. (1974) · IEEE Transactions on Nuclear Science · doi:10.1109/tns.1974.6499235 · Cited by 2,202

What is the best multi-stage architecture for object recognition?

Jarrett, K., Kavukcuoglu, K., Ranzato, M. A., & LeCun, Y. (2009) · 2009 IEEE 12th International Conference on Computer Vision · doi:10.1109/iccv.2009.5459469 · Cited by 2,153

Multilayer feedforward networks with a nonpolynomial activation function can approximate any function

Leshno, M., Lin, V. Y., Pinkus, A., & Schocken, S. (1993) · Neural Networks · doi:10.1016/s0893-6080(05)80131-5 · Cited by 2,121

Approximation theory of the MLP model in neural networks

Pinkus, A. M. (1999) · Acta Numerica · doi:10.1017/s0962492900002919 · Cited by 1,638

A Function Space Analysis of Finite Neural Networks With Insights From Sampling Theory

Giryes, R. (2022) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2022.3155238 · Cited by 3

Research on state assessment method of key equipment in distribution network

Fang, M., Rui, H., Lv, T., Liu, C., Ding, X., & Wang, P. (2023) · Asia Conference on Power and Electrical Engineering (ACPEE) · doi:10.1109/acpee56931.2023.10135928 · Cited by 3

Explicit representations for Banach subspaces of Lizorkin distributions

Neumayer, S., & Unser, M. A. (2023) · Analysis and Applications · doi:10.1142/s0219530523500148 · Cited by 3

Neuro-fuzzy classifiers

Ломакина, Л. С., & Дмитриевич, Ч. И. (2021) · Modelirovanie, optimizaciâ i informacionnye tehnologii. · doi:10.26102/2310-6018/2021.35.4.027 · Cited by 3

Towards a Framework for Noctilucent Cloud Analysis

Sharma, P. K., Dalin, P. A., & Mann, I. B. (2019) · Remote Sensing · doi:10.3390/rs11232743 · Cited by 3

Greedy Shallow Networks: A New Approach for Constructing and Training Neural NetworksPreprint

Dereventsov, A., Petrosyan, A., & Webster, C. (2019) · arXiv (Cornell University) · Cited by 3

Symmetry & critical points for a model shallow neural networkPreprint

Arjevani, Y., & Field, M. (2020) · arXiv (Cornell University) · Cited by 3

Nonconvex penalization for sparse neural networksPreprint

Pieper, K., & Petrosyan, A. (2020) · arXiv (Cornell University) · Cited by 3

Activation functions are not needed: the ratio netPreprint

Zhou, C.-C., Tu, H.-L., Hou, Y.-J., Ling, Z., Liu, Y., & Hua, J. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2005.06678 · Cited by 3

On the Number of Linear Functions Composing Deep Neural Network: Towards a Refined Definition of Neural Networks ComplexityPreprint

Takai, Y., Sannai, A., & Cordonnier, M. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2010.12125 · Cited by 3

Ridge Regression with Over-Parametrized Two-Layer Networks Converge to Ridgelet SpectrumPreprint

Sonoda, S., Ishikawa, I., & Ikeda, M. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2007.03441 · Cited by 3

Application of AI and Machine Learning Algorithms in Power System State Estimation

Azimian, B., Biswas, R. S., & Pal, A. (2025) · doi:10.1002/9781394334599.ch5 · Cited by 3

Multitarget CFAR Detection Method Based on Neural Network for HF Hybrid Sky-Surface Wave Radar in Weibull Clutter Background

Li, Y., Zhang, W., Wang, P., Yao, T., Ding, B., Wang, Z., & Wang, Z. (2024) · IEEE Sensors Journal · doi:10.1109/jsen.2024.3481006 · Cited by 2

A Dual-Layer Coupled Network Perspective on Shared-Aperture Transparent Antenna Arrays for Integrated Space-Air-Ground Networks

Feng, Y., Wu, Y., & Jia, L. (2025) · IEEE Transactions on Network Science and Engineering · doi:10.1109/tnse.2025.3606483 · Cited by 2

Real-Time Human Pose Estimation via Cascaded Neural Networks Embedded with Multi-task Learning

Tanabe, S., Yamanaka, R., Tomono, M., Ito, M., & Ishihara, T. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-64698-5_21 · Cited by 2

Deep Neural Network Surrogates for Optimal Design of Helicopter Rotor

Sarawagi, S., & Ganguli, R. (2021) · Transactions of Indian National Academy of Engineering · doi:10.1007/s41403-021-00227-w · Cited by 3

Approximation of neural network operators based on the Joukowski transformation

Jin, M., Xiang, D., & Yu, D. (2024) · International Journal of Wavelets Multiresolution and Information Processing · doi:10.1142/s0219691324500474 · Cited by 2

A Comprehensive Analysis of Fast-Food Classification Using You Only Look Once (YOLO) Model

Bandyopadhyay, S., Dutta, D., & Pratihar, S. (2024) · International Conference on Computing, Communication and Networking Technologies (ICCCNT) · doi:10.1109/icccnt61001.2024.10724136 · Cited by 2

Fixed time stabilization of stochastic neutral-type fuzzy inertial neural network with mixed delays

Fang, W., Xie, T., Zhu, Q., & Huang, T. (2025) · Fuzzy Sets and Systems · doi:10.1016/j.fss.2025.109566 · Cited by 2

Center Manifold Analysis of Plateau Phenomena Caused by Degeneration of Three-Layer Perceptron

Tsutsui, D. (2020) · Neural Computation · doi:10.1162/neco_a_01268 · Cited by 2

A Sequential Framework Towards an Exact SDP Verification of Neural Networks

Ma, Z., & Sojoudi, S. (2021) · IEEE International Conference on Data Science and Advanced Analytics (DSAA) · doi:10.1109/dsaa53316.2021.9564161 · Cited by 2

ELM based architecture for general purpose automatic weight and structure learning

de Andrade, D. C., & Trabasso, L. G. (2017) · Neurocomputing · doi:10.1016/j.neucom.2017.09.026 · Cited by 2

On the double windowed ridgelet transform and its inverse

Fujii, K., & Kinoshita, T. (2019) · Integral Transforms and Special Functions · doi:10.1080/10652469.2019.1675059 · Cited by 2

Deep learning approaches to mid-term forecasting of social-economic and demographic effects of a pandemic

Devyatkin, D. A., Otmakhova, Y. S., Ивановна, У. Н., Соченков, И. В., & Budzko, V. I. (2021) · Procedia Computer Science · doi:10.1016/j.procs.2021.06.020 · Cited by 2

Enhancing 3D implicit shape representation by leveraging periodic activation functions

Singla, K., & Astya, P. (2021) · International Conference on Signal Processing, Computing and Control (ISPCC) · doi:10.1109/ispcc53510.2021.9609352 · Cited by 2

Disentangling private classes through regularization

Tartaglione, E., Gennari, F., Quétu, V., & Grangetto, M. (2023) · Neurocomputing · doi:10.1016/j.neucom.2023.126612 · Cited by 2

Data-Driven Initial Gap Identification of Piecewise-Linear Systems Using Sparse Regression and Universal Approximation Theorem

Kanki, R., & Saito, A. (2024) · Journal of Computational and Nonlinear Dynamics · doi:10.1115/1.4065440 · Cited by 2

Web-aided data set expansion in deep learning: evaluating trainable activation functions in ResNet for improved image classification

Zhang, Z., Li, X., Xu, X., Lu, C., Yang, Y., & Shi, Z. (2024) · International Journal of Web Information Systems · doi:10.1108/ijwis-05-2024-0135 · Cited by 2

Distributed Learning of Deep Sparse Neural Networks for High-dimensional Classification

Garg, S., Krishnan, R., Jagannathan, S., & Samaranayake, V. A. (2018) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata.2018.8621888 · Cited by 2

The Shearlet Transform and Lizorkin Spaces

Bartolucci, F., Pilipović, S., & Teofanov, N. (2020) · Applied and numerical harmonic analysis · doi:10.1007/978-3-030-56005-8_3 · Cited by 2

Universal approximation properties for an ODENet and a ResNet: Mathematical analysis and numerical experiments

Aizawa, Y., Kimura, M., & Matsui, K. (2023) · Discrete and Continuous Dynamical Systems - B · doi:10.3934/dcdsb.2023099 · Cited by 5

Piecewise linear functions representable with infinite width shallow ReLU neural networks

McCarty, S. (2023) · Proceedings of the American Mathematical Society Series B · doi:10.1090/bproc/186 · Cited by 1

Universal embedding of autonomous dynamical systems into a Lotka-Volterra-like format

Frezzato, D. (2023) · Physica Scripta · doi:10.1088/1402-4896/ad1236 · Cited by 1

Aspects of Importance Sampling in Parameter Selection for Neural Networks Using Ridgelet Transform

Homma, H., & Ohkubo, J. (2024) · Journal of the Physical Society of Japan · doi:10.7566/jpsj.93.124001 · Cited by 1

Interpreting Deep Neural Network-Based Receiver Under Varying Signal-To-Noise Ratios

Tuononen, M., Korpi, D., & Hautamäki, V. (2025) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49660.2025.10888682 · Cited by 1

Modelling the Interactions Between Resources and Academic Achievement: An Artificial Neural Network Approach

Han, C. D., Phillipson, S. N., & Lee, V. C. S. (2025) · Education Sciences · doi:10.3390/educsci15050519 · Cited by 2

Approximation of functions of several variables by deep operators activated by sigmoidal functions and rectified power units

Costarellı, D. (2025) · Rendiconti del Circolo Matematico di Palermo Series 2 · doi:10.1007/s12215-025-01245-1 · Cited by 1

Global attractivity criteria for a discrete-time Hopfield neural network model with unbounded delays via singular M—matrices

Oliveira, J. J., & Teixeira, A. S. (2025) · Neurocomputing · doi:10.1016/j.neucom.2025.131311 · Cited by 1

AI Control for Pasteurized Soft-Boiled Eggs

Podržaj, P., Kozjek, D., Škulj, G., Požrl, T., & Jenko, M. (2025) · Foods · doi:10.3390/foods14183171 · Cited by 1

Classification of adrenocortical carcinoma, pheochromocytoma, and adrenal adenomas using contrast-enhanced computed tomography with machine learning and texture features: a cross-sectional study

Manaev, A. V., Tarbaeva, N. V., Алексеевна, Б. С., Дмитриевна, К. Л., Владимировна, Х. А., Urusova, L., Владимеровна, П. Н., Mel'nichenko, G. A., Mokrysheva, N., & Sinitsyn, V. E. (2025) · Digital Diagnostics · doi:10.17816/dd659812 · Cited by 1

Bayesian neural networks with interpretable priors from Mercer kernels

Alberts, A., & Bilionis, I. (2026) · Computer Methods in Applied Mechanics and Engineering · doi:10.1016/j.cma.2026.118896 · Cited by 1

Robust Phase Synthesis of X-Band Transmissive Metasurface Unit Cells Using Unit-Circle Surrogates and Loxo-X₃ Validation

Malkoç, M., & Turhal, Ü. Ç. (2026) · Journal of Electrical Engineering and Technology · doi:10.1007/s42835-026-02915-5 · Cited by 1

Automatic Speech Recognition Based on Neural Networks

Schlüter, R., Doetsch, P., Golik, P., Kitza, M., Menne, T., Irie, K., Tüske, Z., & Zeyer, A. (2016) · Lecture notes in computer science · doi:10.1007/978-3-319-43958-7_1 · Cited by 1

The Role of Nonpolynomiality in Uniform Approximation by RBF Networks of Hankel Translates

Marrero, I. (2019) · Journal of Function Spaces · doi:10.1155/2019/1845491 · Cited by 1

Self-Organizing Multilateration of an Unknown Number of Transmitters

McClintick, K. W., Tolbert, J., & Wyglinski, A. M. (2022) · IEEE Open Journal of Vehicular Technology · doi:10.1109/ojvt.2022.3152699 · Cited by 1

Stable emotional adaptive neuro-control of uncertain affine nonlinear systems with input saturation

Baghbani, F., & Totonchi, M. R. A. (2023) · Neural Computing and Applications · doi:10.1007/s00521-023-08725-4 · Cited by 1

A Continuous Transform for Localized Ridgelets

Shenouda, J., Parhi, R., & Nowak, R. D. (2023) · International Conference on Sampling Theory and Applications · doi:10.1109/sampta59647.2023.10301398 · Cited by 1

Global Universality of the Two-Layer Neural Network with the k -Rectified Linear Unit

Hatano, N., Ikeda, M., Ishikawa, I., & Sawano, Y. (2024) · Journal of Function Spaces · doi:10.1155/2024/3262798 · Cited by 1

Machine-Learning Modelling of a Fluid Flow in a Two-Dimensional Channel

Aravanis, T. I., Chrimatopoulos, G., Xenos, M. A., & Tzirtzilakis, E. E. (2024) · International Conference on Information, Intelligence, Systems & Applications (IISA) · doi:10.1109/iisa62523.2024.10786684 · Cited by 1

Semi-periodic Activation for Time Series Classification

Júnior, J. G. B. D. M., de Mitri, A. G., & Silva, D. F. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-79038-6_6 · Cited by 1

A deep neural network two-part model and feature importance test for semicontinuous data

Zou, B., Mi, X., Wan, S., Wu, D., Xenakis, J. G., Hu, J., & Zou, F. (2025) · The Annals of Applied Statistics · doi:10.1214/25-aoas2013 · Cited by 1

Rapid Risk Minimization with Bayesian Models Through Deep Learning Approximation

Löwe, M., Lunnemann, P., & Risi, S. (2021) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn52387.2021.9534258 · Cited by 1

Universal approximation with neural networks on function spaces

Kumagai, W., Sannai, A., & Kawano, M. (2022) · Journal of Experimental & Theoretical Artificial Intelligence · doi:10.1080/0952813x.2022.2123563 · Cited by 1

Neuro-fuzzy classification of technical conditions of objects of complex structure

Манцеров, С. А. (2023) · INFORMACIONNYE TEHNOLOGII · doi:10.17587/it.29.91-97 · Cited by 1

Decoding Stacked Denoising Autoencoders.Preprint

Sonoda, S., & Murata, N. (2016) · arXiv (Cornell University) · Cited by 1

Learning Distributions of Meant Color.Preprint

White, L., Togneri, R. B., Liu, W., & Bennamoun, M. (2017) · arXiv (Cornell University) · Cited by 1

Integral representation of shallow neural network that attains the global minimum.Preprint

Sonoda, S., Ishikawa, I., Ikeda, M., Hagihara, K., Sawano, Y., Matsubara, T., & Murata, N. (2018) · arXiv (Cornell University) · Cited by 1

Knots in random neural networksPreprint

Chen, K. K., Gamst, A. C., & Walker, A. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1811.11152 · Cited by 1

Learning of Colors from Color Names: Distribution and Point EstimationPreprint

White, L., Togneri, R. B., Liu, W., & Bennamoun, M. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1709.09360 · Cited by 6

Fast Approximation and Estimation Bounds of Kernel Quadrature for Infinitely Wide ModelsPreprint

Sonoda, S. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1902.00648 · Cited by 3

An Accelerated Fitted Value Iteration Algorithm for MDPs with Finite and Vector-Valued Action SpacePreprint

Zhao, S., Haskell, W. B., & Cardin, M. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1901.05154 · Cited by 1

Learning and Subjective Expectation Formation: A Recurrent Neural Network ApproachPreprint

Hou, C. (2021) · SSRN Electronic Journal · doi:10.2139/ssrn.3728129 · Cited by 1

BAMCAFE: A Bayesian Machine Learning Advanced Forecast Ensemble Method for Complex Nonlinear Turbulent Systems with Partial ObservationsPreprint

Chen, N., & Li, Y. (2021) · arXiv (Cornell University) · Cited by 1

Identificação e controle de sistemas dinâmicos com rede neural paraconsistente.

de Carvalho, A. (2021) · doi:10.11606/t.3.2021.tde-08102021-100149 · Cited by 1

A Minimax Approach for Classification with Big-data

Krishnan, R., Jagannathan, S., & Samaranayake, V. A. (2018) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata.2018.8622564

Copula Representations and Error Surface Projections for the Exclusive Or ProblemPreprint

Freedman, R. S. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1907.04483

Universal Function Approximation on Graphs using Multivalued Functions.

Gabrielsson, R. B. (2020)

Forecasting the USD/SEK exchange rate using deep neural networks

Hamfelt, T. (2019) · Lund University Publications Student Papers (Lund University)

Lyndon White, Roberto Togneri, Wei Liu and Mohammed Bennamoun, Neural Representations of Natural Language. Singapore, Springer, 2019. XIV + 122 pages, ISBN:9789811300615

Feng, H. (2020) · Natural Language Engineering · doi:10.1017/s1351324920000248

No one-hidden-layer neural network can represent multivariable functionsPreprint

Inoue, M., Futamura, M., & Ninomiya, H. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2006.10977

Mathematical Theory of Neural Network Models for Machine Learning

Ma, C. (2020)

Universal Approximation with Neural Intensity Point Processes.Preprint

Soen, A., Mathews, A. P., Grixti-Cheng, D., & Xie, L. (2020) · arXiv (Cornell University)

Cue word guided question generation with BERT model fine-tuned on natural question dataset

Zhang, Z. (2020) · Research Commons (University of Waikato)

Some Generalizations of Radon Transforms

藤井, 克., フジイ, カ., & Fujii, K. (2019) · Institutional Repositories DataBase (IRDB) · doi:10.15068/00156516

Ghosts in Neural Networks: Existence, Structure and Role of Infinite-Dimensional Null SpacePreprint

Sonoda, S., Ishikawa, I., & Ikeda, M. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2106.04770 · Cited by 5

Pointspectrum: Equivariance Meets Laplacian Filtering for Graph Representation Learning

Poiitis, M., Sermpezis, P., & Vakali, A. I. (2022) · IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology (WI-IAT) · doi:10.1109/wi-iat55865.2022.00053

Energy Conservation in Infinitely Wide Neural-Networks

Eguchi, S., & Amaba, T. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-86380-7_15

Learning to Control using Image FeedbackPreprint

Raghavan, K., Narayanan, V., & Jagannathan, S. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2110.15290

A Sequential Framework Towards an Exact SDP Verification of Neural NetworksPreprint

Ma, Z., & Sojoudi, S. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2010.08603

A Discussion on the Scalability of Heuristic Approximators (Extended Abstract)

Pendurkar, S., Huang, T., Koenig, S., & Sharon, G. (2022) · Proceedings of the International Symposium on Combinatorial Search · doi:10.1609/socs.v15i1.21796

405. Genomic prediction of longitudinal body weights in pigs using a neural network

Ni, Z., Fernando, R. L., Yu, H., Knol, E. F., & Dekkers, J. C. M. (2022) · World Congress on Genetics Applied to Livestock Production (WCGALP) · doi:10.3920/978-90-8686-940-4_405

Hilbert C∗-Module for Analyzing Structured Data

Hashimoto, Y., Komura, F., & Ikeda, M. (2023) · Mathematics online first collections · doi:10.1007/16618_2023_58

PERFORMANCE EVALUATION OF 7TH GRADE STUDENTS FOR SOCIAL SCIENCE EDUCATION (IPS) UTILISING SUPPORT VECTOR MACHINE (SVM) METHOD

Kristina, J., & Hiskiawan, P. (2023) · JURNAL GEOGRAFI Geografi dan Pengajarannya · doi:10.26740/jggp.v21n2.p129-142

A Comprehensive Review of Artificial Intelligence Based Algorithm Towards Fetal Facial Anomalies DetectionPreprint

Sriraam, N., Chinta, B., Suresh, S., & Sudharshan, S. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4812061

Noncommutative C*-Algebra Net: Learning Neural Networks with Powerful Product Structure in C*-AlgebraPreprint

Hataya, R., & Hashimoto, Y. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4895567 · Cited by 4

All-optical control-flow and enhancement of optical neural networks

Kissner, M., Ghalanos, G. N., Caruana, P., & Bino, L. D. (2024) · Emerging Topics in Artificial Intelligence (ETAI) · doi:10.1117/12.3027753

Koopman Dynamic Modeling for Global and Unified Representations of Rigid Body Systems Making and Breaking Contact

O’Neill, C., & Asada, H. H. (2024) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros58592.2024.10801737

An Approximate-and-Optimize Method for Security-Constrained AC Optimal Power Flow

Xiong, J., Lei, S., Wang, A., & Luo, X. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-75623-8_34

Constructive Universal Approximation Theorems for Deep Neural Networks: A Group Representation Theoretical Approach

Sonoda, S. (2024) · The Brain & Neural Networks · doi:10.3902/jnns.31.177

Neural networks and deep learning: part I

Theodoridis, S. (2025) · Elsevier eBooks · doi:10.1016/b978-0-44-329238-5.00024-x

Universal approximation property of ODENet and ResNet with a single activation function

Kimura, M., Matsui, K., & Mizuno, Y. (2025) · Journal of Computational Mathematics and Data Science · doi:10.1016/j.jcmds.2025.100116

Optimizing Training Hyperparameters for Multilayer Perceptrons in Deep Learning

Echamsi, S., Belouafi, E., Kassimi, A. E. B., Alali, A., Bouroumi, A., & Guennoun, A. (2025) · International Conference on Innovative Research in Applied Science, Engineering and Technology (IRASET) · doi:10.1109/iraset64571.2025.11008006 · Cited by 1

Supervised Learning of Random Neural Architectures Structured by Latent Random Fields on Compact Boundaryless Multiply-Connected ManifoldsPreprint

Soize, C. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5397462

Schizophrenia Diagnosis Support with Spectral and Cepstral Features of Speech

Teixeira, F., Mendes, J., Soares, S., Abreu, J. L. P., & Teixeira, J. P. (2025) · Communications in computer and information science · doi:10.1007/978-3-032-00137-5_12

Approximate oblique dual frames in separable Q-Hilbert spaces

Tian, Y., & Zhang, W. (2025) · The Journal of Analysis · doi:10.1007/s41478-025-00973-y

The cost of simplification: Comparing surrogate electrolyser models in a MILP framework

Fordham, D., Llamas‐Jansa, I., & Ulleberg, Ø. (2025) · Energy Conversion and Management X · doi:10.1016/j.ecmx.2025.101433

Shape-aware deep learning for models of production

Wei, Z., Sang, H., Prokhorov, A. B., & Ma, Y. (2026) · Journal of Productivity Analysis · doi:10.1007/s11123-026-00797-3 · Cited by 1

Research on the intelligent assistance design technology for planing craft based on neural networks

Zhang, Z., Zhou, T., Guo, C., Yang, C., Huang, W., Sun, J., & Zhang, Z. (2026) · Ocean Engineering · doi:10.1016/j.oceaneng.2026.124889

Classification de données massives de télédétection

Audebert, N. (2018) · theses.fr (ABES) · doi:10.70675/e7e6756dzea11z49c1z99dfz2a794a46b421

Advances in Deep Neural Architectures for Hyperspectral Image Analysis

Paoletti, M. E., & Wu, Z. (2026) · Advances in computer vision and pattern recognition · doi:10.1007/978-981-95-2038-1_2

Neural Network with Unbounded Activations is Universal Approximator

Sonoda, S., & Murata, N. (2015) · Cited by 8

Constructive Universal Approximation by Infinite-Dimensional Neural Networks via Gaussian-Weighted Ridgelet TransformPreprint

Sonoda, S., Galimberti, L., Xu, Y., Ishikawa, I., & Ikeda, M. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2610.24293

Approximation capabilities of neural networks on unbounded domains

Wang, M., & Qu, Y. (2021) · Neural Networks · doi:10.1016/j.neunet.2021.10.001 · Cited by 16

ReLU Network with Bounded Width Is a Universal Approximator in View of an Approximate Identity

Moon, S. (2021) · Applied Sciences · doi:10.3390/app11010427 · Cited by 15

Universal approximation results for neural networks with non-polynomial activation function over non-compact domains

Neufeld, A., & Schmocker, P. (2025) · Analysis and Applications · doi:10.1142/s0219530525500423 · Cited by 10