𝔖 Bobbio Scriptorium
✦   LIBER   ✦

Feedforward neural networks for principal components extraction

✍ Scribed by Sandro Nicole

Publisher
Elsevier Science
Year
2000
Tongue
English
Weight
233 KB
Volume
33
Category
Article
ISSN
0167-9473

No coin nor oath required. For personal study only.

✦ Synopsis

In recent times, an upsurge of interest in the study of artiΓΏcial neural networks apt to computing a principal component extraction has been observed. The present work is devoted to the description and performance analysis (by means of computer simulations) of some neural networks of such a kind. The main conclusion reached is that, while the ΓΏrst principal component is almost always e ciently obtained, lesser components tends to be sloppily approximated. All the nets considered here share the interesting feature of being endowed with a feedforward connectivity, together with an Hebbian law of synaptic weights' adjustment. Their potential usefulness as modular tools, to be inserted in more complex models of psychological and neurological functions has been suggested. There is, however, for the time being no clear evidence supporting any real biological implementation of these simple computational architectures.

πŸ“œ SIMILAR VOLUMES

Principal components, minor components,
Principal components, minor components, and linear neural networks
✍ Erkki Oja πŸ“‚ Article πŸ“… 1992 πŸ› Elsevier Science 🌐 English βš– 731 KB

## Many neural network realizations have been recently proposed for the statistical technique of Principal Component Analysis ( PCA ). Explicit connections between numerical constrained adaptive algorithms and neural networks with constrained Hebbian learning rules art, reviewed. The Stochastic Gr

DIAGNOSTIC RULE EXTRACTION FROM TRAINED
DIAGNOSTIC RULE EXTRACTION FROM TRAINED FEEDFORWARD NEURAL NETWORKS
✍ YIMIN FAN; C.JAMES LI πŸ“‚ Article πŸ“… 2002 πŸ› Elsevier Science 🌐 English βš– 272 KB

This paper describes a method of extracting diagnostic rules from trained diagnostic feedforward neural nets that are constructed to recognise di!erent mechanical faults using automated weight and structure learning algorithms. The rule extracting method is based on an interpretation that considers