Approximation by superpositions of a sigmoidal function

1989/12/01 by George Cybenko, G. Cybenko · 32 citations
Computer Science · Engineering · #Fault Detection and Control Systems #Fuzzy Logic and Control Systems #Neural Networks and Applications

paper · doi:10.1007/bf02551274

crossref issued 1989/12/01 · crossref published 1989/12/01 · crossref published-print 1989/12/01 · openalex publication_date 1989/12/01 · crossref created 2007/01/05 · crossref deposited 2023/05/10 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/04 · crossref indexed 2026/08/04

Citations

• Multilayer feedforward networks are universal approximators

Cited by

• Two geometric input transformation methods for fast online reinforcement learning with neural nets
• Coded-InvNet for Resilient Prediction Serving Systems
• Analytical aspects of non-differentiable neural networks
• Universal discrete-time reservoir computers with stochastic inputs and\n linear readouts using non-homogeneous state-affine systems
• Stress-Testing Neural Models of Natural Language Inference with Multiply-Quantified Sentences
• Universal Approximation of Markov Kernels by Shallow Stochastic Feedforward Networks
• Deep learning to infer eddy heat fluxes from sea surface height patterns of mesoscale turbulence
• A Tutorial about Random Neural Networks in Supervised Learning
• How Implicit Regularization of ReLU Neural Networks Characterizes the\n Learned Function -- Part I: the 1-D Case of Two Layers with Random First\n Layer
• WGAN with an Infinitely Wide Generator Has No Spurious Stationary Points
• Compression based bound for non-compressed network: unified generalization error analysis of large compressible deep neural network
• UNIPoint: Universally Approximating Point Processes Intensities
• Integral Representations of Sobolev Spaces via ReLU^k Activation Function and Optimal Error Estimates for Linearized Networks
• Patterns, predictions, and actions: A story about machine learning
• Spatial Variability Aware Deep Neural Networks (SVANN): A General Approach
• A deep neural network approach on solving the linear transport model under diffusive scaling
• Deep Neural Networks for Choice Analysis: A Statistical Learning Theory Perspective
• Multimodal Data Fusion based on the Global Workspace Theory
• Convergence of a Robust Deep FBSDE Method for Stochastic Control
• The evolutionary origins of modularity
• From expNN to sinNN: automatic generation of sum-of-products models for potential energy surfaces in internal coordinates using neural networks and sparse grid sampling
• Approximation with random bases: Pro et Contra
• Significant wave height record extension by neural networks and reanalysis wind data
• Statistical and Predictive Analysis to Identify Risk Factors and Effects of Post COVID-19 Syndrome
• Agentic Symbolic Search: Characterizing PDEs Beyond Hand-crafted Expressions, Meshes, and Neural Networks
• The CAMELS Multifield Data Set: Learning the Universe’s Fundamental Parameters with Artificial Intelligence
• Two-parameter superposable S-curves
• AI Supply Chains: An Emerging Ecosystem of AI Actors, Products, and Services
• FiberKAN: Kolmogorov-Arnold Networks for Nonlinear Fiber Optics
• Non-identifiability distinguishes Neural Networks among Parametric Models
• Analysis of the correlation structure for a neural predictive model with application to speech recognition
• George Cybenko [wikipedia]