✦ LIBER ✦

Design of an auto-associative neural network by using design of experiments approach

✍ Scribed by Božidar Bratina; Nenad Muškinja; Boris Tovornik

Publisher: Springer-Verlag
Year: 2009
Tongue: English
Weight: 604 KB
Volume: 19
Category: Article
ISSN: 0941-0643
DOI: 10.1007/s00521-009-0287-6

No coin nor oath required. For personal study only.

📜 SIMILAR VOLUMES

Reuse of CAD designs by a neural-network

Reuse of CAD designs by a neural-network approach

✍ Andreas Scherer 📂 Article 📅 1996 🏛 Elsevier Science 🌐 English ⚖ 717 KB

The optimisation of neural network param

The optimisation of neural network parameters using Taguchi’s design of experiments approach: an application in manufacturing process modelling

✍ Wimalin Sukthomya; James Tannock 📂 Article 📅 2005 🏛 Springer-Verlag 🌐 English ⚖ 235 KB

On the design of artificial auto-associa

On the design of artificial auto-associative neuronal networks

✍ Stefan Reimann 📂 Article 📅 1998 🏛 Elsevier Science 🌐 English ⚖ 502 KB

In this paper, we consider the problem of how to construct an artificial neuronal network such that it reproduces a given set of patterns in an exact manner. It turns out that the structure of the weight matrix of the network represents the structure of the set of patterns it is acting on, not the p

Training the neocognitron network using

Training the neocognitron network using design of experiments

✍ Ming-Yeong Teo; Siang-Kok Sim 📂 Article 📅 1995 🏛 Elsevier Science 🌐 English ⚖ 995 KB

Neocognitron is a hierarchically structured multi-layer neural network that is recognised for its ability to tolerate scaling and rotational effects of the input patterns. However, there are many parameters that describe the hierarchical multi-layer structure of the network which must be adjusted pr

Comparison of experimental designs using

Comparison of experimental designs using neural networks

✍ Yun Lin; Zisheng Zhang; Jules Thibault 📂 Article 📅 2009 🏛 John Wiley and Sons 🌐 English ⚖ 123 KB

## Abstract Experimental designs were compared using stacked‐layer feed‐forward neural networks. Several traditional three‐level designs and uniform designs were investigated using three‐factor linear and nonlinear models. The prediction error was found to be inversely proportional to the number of

Neural network approach for comodeling d

Neural network approach for comodeling design of multichip module

✍ M. El Zoghbi; D. Baillargeat; S. Bila; S. Verdeyme; J. F. Villemazet 📂 Article 📅 2008 🏛 John Wiley and Sons 🌐 English ⚖ 532 KB

## Abstract An original comodeling approach based on neural network is proposed in order to optimize multichip modules (MCM). This approach permits to characterize and to optimize millimeter‐wave module behavior by taking into account electromagnetic phenomena. All the design procedure is implement