Approximation capabilities of multilayer feedforward networks
Explore this paper's citation graph
Summary
It is shown that standard multilayer feedforward networks with as few as a single hidden layer and arbitrary bounded and nonconstant activation function are universal approximators with respect to L p (μ) performance criteria, for arbitrary finite input environment measures μ.
- Type
- article
- Published
- 1991-03-01
- Cited by
- 6,541
- References
- 12
- OpenAlex
- https://openalex.org/W1988115241
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:7343126
Keywords
Feed forward, Computer science, Feedforward neural network, Artificial intelligence, Artificial neural network
References
- There exists a neural network that does not make avoidable mistakes
- On the approximate realization of continuous mappings by neural networks
- Construction of neural nets using the radon transform
- Original Contribution: On learning the derivatives of an unknown mapping with multilayer feedforward networks
- Universal approximation of an unknown mapping and its derivatives using multilayer feedforward networks
- Universal approximation using feedforward networks with non-sigmoid hidden layer activation functions
- Approximation by superpositions of a sigmoidal function
- Multilayer feedforward networks are universal approximators
- Approximating and learning unknown mappings using multilayer feedforward networks with bounded weights
- Theory of the Back Propagation Neural Network
- Multilayer feedforward networks are universal approximators
- Fourier Analysis on Groups
Cited by
- A Tour of Advanced Data Mining Methodologies: The CART Decision Tree
- Shear strength prediction using dimensional analysis and functional networks
- A review of feedforward neural networks in transportation research
- A hybrid method for parameter estimation and its application to biomedical systems
- A Neural Network Approach for Forestal Fire Risk Estimation
- Neural Network L 1 Adaptive Control of MIMO Systems with Nonlinear Uncertainty
- A New Conceptual Automated Property Valuation Model for Residential Housing Market
- A study of prediction in seabed mapping
- Combining complementary neural network and error-correcting output codes for multiclass classification problems
- Universal Approximation Theorem for Interval Neural Networks
- Constructive feedforward neural networks for regression problems : a survey
- On Development of Some Soft Computing Based Multiuser Detection Techniques for SDMA–OFDM Wireless Communication System
- Rafraîchissement par la ventilation naturelle traversante des bâtiments en climat méditerranéen
- Autonomously Reconfigurable Artificial Neural Network on a Chip
- Neural Networks and Analog Computation
- Development of an intelligent inspection system for detecting and classifying garment defects
- Real-Time Midcourse Guidance Robust to Missile Launch Conditions
- Approaches to combining local and evolutionary search for training neural networks: a review and some new results
- Some Topics in Neural Networks and Control
- Forecasting high-frequency time series with neural networks - an analysis of modelling challenges from increasing data frequency
Related papers
- FIR and IIR Synapses, a New Neural Network Architecture for Time Series Modeling
- A Study of Teachers Evaluation Model Based on Combination Neural Network
- A design approach for feedback-feedforward control systems
- Model of NW Multilayer Feedforward Small-World Artificial Neural Networks and It's Applied
- 신경회로망의 쟈코비안을 이용한 Feedforward/Feedback 병합제어기 설계 ( The Combined Feedforward/Feedback Controller Design Using Jacobians of Neural Network )
- Representational Capabilities of Multilayer Feedforward Networks with Time-Delay Synapses
- A genetic algorithm based neural-tuned neural network
- Design of a feedforward controller for AFM nanopositioning based on neural network control theory