𝔖 Bobbio Scriptorium
✦   LIBER   ✦

Training the neocognitron network using design of experiments

✍ Scribed by Ming-Yeong Teo; Siang-Kok Sim

Publisher
Elsevier Science
Year
1995
Tongue
English
Weight
995 KB
Volume
9
Category
Article
ISSN
0954-1810

No coin nor oath required. For personal study only.

✦ Synopsis

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 properly for the network to recognise a set of patterns to allow for their scaling and rotational effects.

The methodology utilises an orthogonal array to determine combination of values of the various parameters, instead of all the possible combinations, thus greatly reducing the number of trials required to arrive at the optimum values.

πŸ“œ SIMILAR VOLUMES

Design of experiments using the microcyt
Design of experiments using the microcytotoxicity assay
✍ Joseph P. Brown; Gerald Van Belle; Ingegerd HellstrΓΆm πŸ“‚ Article πŸ“… 1976 πŸ› John Wiley and Sons 🌐 French βš– 545 KB

## Abstract Examination of data from the microcytotoxicity assay revealed that the number of surviving target cells varies systematically both between microtest plates and within plates. If the layout of treatments on the plate is not planned carefully, these effects decrease precision and introduc

The design of a flotation network using
The design of a flotation network using inequalities
✍ James C.A. Green πŸ“‚ Article πŸ“… 1982 πŸ› Elsevier Science 🌐 English βš– 436 KB

matrix inequality in terms of the row sums of a matrix has been applied to the configurational design of a flotation network. Each row sum refers to a given cell in the network. Each row sum is a function of circuit connections and cell operating conditions. By varying the row sums, variable upper