✦ LIBER ✦

Approximation of a function and its derivative with a neural network

✍ Scribed by Pierre Cardaliaguet; Guillaume Euvrard

Publisher: Elsevier Science
Year: 1992
Tongue: English
Weight: 998 KB
Volume: 5
Category: Article
ISSN: 0893-6080
DOI: 10.1016/s0893-6080(05)80020-6

No coin nor oath required. For personal study only.

✦ Synopsis

This paper deals with the approximation of both a function and its derivative by feedforward neural networks. We propose an explicit formula of approximation which is noise resistant and can be easily modified with the patterns. We apply these results to approach a function defined implicitly, which is useful in control theory.

📜 SIMILAR VOLUMES

Properties and performance of orthogonal

Properties and performance of orthogonal neural network in function approximation

✍ Chieh F. Sher; Ching-Shiow Tseng; Chen-San Chen 📂 Article 📅 2001 🏛 John Wiley and Sons 🌐 English ⚖ 216 KB

Backpropagation neural network has been applied successfully to solving uncertain problems in many fields. However, unsolved drawbacks still exist such as the problems of local minimum, slow convergence speed, and the determination of initial weights and the number of processing elements. In this pa

A feedforward neural network with functi

A feedforward neural network with function shape autotuning

✍ Chyi-Tsong Chen; Wei-Der Chang 📂 Article 📅 1996 🏛 Elsevier Science 🌐 English ⚖ 814 KB

Approximation of inverse system (many-va

Approximation of inverse system (many-valued function) by neural network

✍ Masakazu Shinki; Kiyotaka Shimizu 📂 Article 📅 2001 🏛 John Wiley and Sons 🌐 English ⚖ 289 KB

Neural network approximation of continuo

Neural network approximation of continuous functionals and continuous functions on compactifications

✍ M.B. Stinchcombe 📂 Article 📅 1999 🏛 Elsevier Science 🌐 English ⚖ 164 KB

This article characterizes the set of activation functions, bounded or unbounded, that allow feedforward network approximation of the continuous functions on the classic two-point compactification of R 1 . The characterization fails when the set of targets are continuous functions on the classic com

A unified approach for neural network-li

A unified approach for neural network-like approximation of non-linear functionals

✍ Tianping Chen 📂 Article 📅 1998 🏛 Elsevier Science 🌐 English ⚖ 56 KB

In this paper, we give a universal approach to approximation of non-linear functionals and so called myopic input-output maps by neural network-like architectures. Strong theorems on equi-uniform approximation to functionals in abstract spaces are given. As applications, theorems on identification o

A symbolic method for network function a

A symbolic method for network function approximation with order reduction

✍ Aguirre, Idoia; Carlosena, Alfonso 📂 Article 📅 2000 🏛 John Wiley and Sons 🌐 English ⚖ 160 KB

This letter presents a method to approximate a symbolic network function of any order to a second-order one. The method is based on the symbolic calculation of the displacement of the main roots of a polynomial due to the variations of a given parameter, assuming the ideal circuit (polynomial) of or