Automatic structure and parameter training methods for modeling of mechanical systems by recurrent neural networks.

DOI10.1016/S0307-904X(99)00020-7zbMath1062.70614OpenAlexW2064092773MaRDI QIDQ1960778

Tung-Yung Huang, C. James Li

Publication date: 26 April 2000

Published in: Applied Mathematical Modelling (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/s0307-904x(99)00020-7

Mathematics Subject Classification ID

Control of mechanical systems (70Q05)

Related Items

Genetically optimized fuzzy polynomial neural networks with fuzzy set-based polynomial neurons, Genetically optimized hybrid fuzzy set based polynomial neural networks, A new approach to self-organizing fuzzy polynomial neural networks guided by genetic optimization, Multi-layer self-organizing polynomial neural networks and their development with the use of genetic algorithms, The design of self-organizing neural networks based on PNS and FPNs with the aid of genetic optimization and extended GMDH method

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Multilayer feedforward networks are universal approximators
• Mechanical system modelling using recurrent neural networks via quasi- Newton learning methods
• Dynamic Recurrent Neural Networks for Control of Unknown Nonlinear Systems
• A New Feedforward Neural Network Structural Learning Algorithm—Augmentation by Training With Residuals
• Neural networks and physical systems with emergent collective computational abilities.
• Neurons with graded response have collective computational properties like those of two-state neurons.
• A Family of Variable-Metric Methods Derived by Variational Means
• A new approach to variable metric algorithms
• The Convergence of a Class of Double-rank Minimization Algorithms 1. General Considerations
• Conditioning of Quasi-Newton Methods for Function Minimization
• Approximation by superpositions of a sigmoidal function