✦ LIBER ✦

Genetic design of sparse feedforward neural networks

✍ Scribed by Swapan Saha; John P. Christensen

Publisher: Elsevier Science
Year: 1994
Tongue: English
Weight: 504 KB
Volume: 79
Category: Article
ISSN: 0020-0255
DOI: 10.1016/0020-0255(94)90119-8

No coin nor oath required. For personal study only.

📜 SIMILAR VOLUMES

Biological engineering applications of f

Biological engineering applications of feedforward neural networks designed and parameterized by genetic algorithms

✍ Konstantinos P. Ferentinos 📂 Article 📅 2005 🏛 Elsevier Science 🌐 English ⚖ 325 KB

Efficient genetic algorithms for trainin

Efficient genetic algorithms for training layered feedforward neural networks

✍ Byungjoo Yoon; Dawn J. Holmes; Gideon Langholz; Abraham Kandel 📂 Article 📅 1994 🏛 Elsevier Science 🌐 English ⚖ 952 KB

Optimization of feedforward neural netwo

Optimization of feedforward neural networks

✍ Jun Han; Claudio Moraga; Stefan Sinne 📂 Article 📅 1996 🏛 Elsevier Science 🌐 English ⚖ 885 KB

A new model of feedforward neural networ

A new model of feedforward neural networks

✍ Dong-Xue Wang; Ju-Wei Tai 📂 Article 📅 1992 🏛 Elsevier Science 🌐 English ⚖ 298 KB

Optimizing the parameters of multilayere

Optimizing the parameters of multilayered feedforward neural networks through Taguchi design of experiments

✍ M. S. Packianather; P. R. Drake; H. Rowlands 📂 Article 📅 2000 🏛 John Wiley and Sons 🌐 English ⚖ 252 KB 👁 1 views

The size and training parameters of artificial neural networks have a critical effect on their performance. This paper presents the application of the Taguchi Design of Experiments (DoEs) off-line quality control method in the optimization of the design parameters of a neural network. Being a 'paral

Design and selection of products via gen

Design and selection of products via genetic algorithms and neural networks

✍ Paola Palmitesta; Corrado Provasi; Cosimo Spera 📂 Article 📅 1999 🏛 John Wiley and Sons 🌐 English ⚖ 129 KB 👁 1 views

In the paper we address the design and selection of products in the framework of genetic algorithms and neural networks. We propose a procedure in alternative to the current methodologies and illustrate its advantages and disadvantages. The results of a real-world application are reported. Although