✦ LIBER ✦

Algorithm for building a neural network for function approximation

✍ Scribed by Jayadeva; Deb, A.K.; Chandra, S.

Book ID: 114447876
Publisher: The Institution of Electrical Engineers
Year: 2002
Tongue: English
Weight: 565 KB
Volume: 149
Category: Article
ISSN: 1350-2409
DOI: 10.1049/ip-cds:20020514

No coin nor oath required. For personal study only.

📜 SIMILAR VOLUMES

An orthogonal neural network for functio

An orthogonal neural network for function approximation

✍ Shiow-Shung Yang; Ching-Shiow Tseng 📂 Article 📅 1996 🏛 IEEE 🌐 English ⚖ 614 KB

A max-piecewise-linear neural network fo

A max-piecewise-linear neural network for function approximation

✍ Chengtao Wen; Xiaoyan Ma 📂 Article 📅 2008 🏛 Elsevier Science 🌐 English ⚖ 394 KB

DEFAnet—A deterministic neural network c

DEFAnet—A deterministic neural network concept for function approximation

✍ Wolfgang J. Daunicht 📂 Article 📅 1991 🏛 Elsevier Science 🌐 English ⚖ 645 KB

Toward generating neural network structu

Toward generating neural network structures for function approximation

✍ Tarek M. Nabhan; Albert Y. Zomaya 📂 Article 📅 1994 🏛 Elsevier Science 🌐 English ⚖ 893 KB

Successive approximation training algori

Successive approximation training algorithm for feedforward neural networks

✍ Y.C. Liang; D.P. Feng; H.P. Lee; S.P. Lim; K.H. Lee 📂 Article 📅 2002 🏛 Elsevier Science 🌐 English ⚖ 110 KB

Cubic approximation neural network for m

Cubic approximation neural network for multivariate functions

✍ Doron Stein; Arie Feuer 📂 Article 📅 1998 🏛 Elsevier Science 🌐 English ⚖ 374 KB

This paper introduces a novel neural network architecture-cubic approximation neural network (CANN), capable of local approximation of multivariate functions. It is particularly simple in concept and in structure. Its simplicity enables a quantitative evaluation of its approximation capabilities, na