A survey on universal approximation and its limits in soft computing techniques.

DOI10.1016/S0888-613X(03)00021-5zbMath1045.68113MaRDI QIDQ1401123

László T. Kóczy, Tamás D. Gedeon, Domonkos Tikk

Publication date: 17 August 2003

Published in: International Journal of Approximate Reasoning (Search for Journal in Brave)

zbMATH Keywords

Kolmogorov's theoremApproximation behaviour of soft computing techniquesApproximation ratesConstructive proofsCourse of dimensionalityNowhere densenessUniversal approximation performed by fuzzy systems and neural networks

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Related Items (13)

Takagi-Sugeno Approximation of a Mamdani Fuzzy System ⋮ Neural dynamic sliding mode control of nonlinear systems with both matched and mismatched uncertainties ⋮ Composite learning control of strict‐feedback nonlinear system with unknown control gain function ⋮ On the inference and approximation properties of belief rule based systems ⋮ A sufficient condition on a general class of interval type-2 Takagi-Sugeno fuzzy systems with linear rule consequent as universal approximators ⋮ Exact analytical inversion of TSK fuzzy systems with singleton and linear consequents ⋮ RSPOP: Rough Set–Based Pseudo Outer-Product Fuzzy Rule Identification Algorithm ⋮ Kernel shapes of fuzzy sets in fuzzy systems for function approximation ⋮ The universal approximation capabilities of double \(2\pi\)-periodic approximate identity neural networks ⋮ How to determine the minimum number of fuzzy rules to achieve given accuracy: a computational geometric approach to SISO case ⋮ On the monotonicity of hierarchical sum-product fuzzy systems ⋮ SISO fuzzy relational inference systems based on fuzzy implications are universal approximators ⋮ Machine learning approach for locating phase interfaces using conductivity probes

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• A simple lemma on greedy approximation in Hilbert space and convergence rates for projection pursuit regression and neural network training
• Approximation by superposition of sigmoidal and radial basis functions
• Universal approximation by hierarchical fuzzy systems
• General Takagi-Sugeno fuzzy systems with simplified linear rule consequent are universal controllers, models and filters
• Sugeno controllers with a bounded number of rules are nowhere dense
• Sugeno type controllers are universal controllers
• A note on universal approximation by hierarchical fuzzy systems
• Stability of interpolative fuzzy KH controllers
• Multilayer feedforward networks are universal approximators
• Approximation theory of fuzzy systems based upon genuine many-valued implications -- SISO cases
• Approximation theory of fuzzy systems based upon genuine many-valued implications -- MIMO cases
• Universal approximation by hierarchical fuzzy system with constraints on the fuzzy rule
• Implications and applications of Kolmogorov's superposition theorem
• Hierarchical fuzzy control
• Universal approximation bounds for superpositions of a sigmoidal function
• ARE FUZZY SYSTEMS UNIVERSAL APPROXIMATORS?
• Outline of a New Approach to the Analysis of Complex Systems and Decision Processes
• On the Structure of Continuous Functions of Several Variables
• Approximation by superpositions of a sigmoidal function

This page was built for publication: A survey on universal approximation and its limits in soft computing techniques.