Weight Assignment Algorithms for Designing Fully Connected Neural Network

Soft computing is used to solve the problems where input data is incomplete or imprecise. This paper demonstrate designing fully connected neural network system using four different weight calculation algorithms. Input data for weight calculation is constructed in the matrix format based on the pair...

Full description

Saved in:
Bibliographic Details
Published in:International journal of intelligent systems and applications 2018-06, Vol.10 (6), p.68-76
Main Authors: Karande, Aarti M., Kalbande, D. R.
Format: Article
Language:English
Subjects:
Algorithms
Linear algebra
Mathematical analysis
Matrix methods
Neural networks
Soft computing
Citations: Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Soft computing is used to solve the problems where input data is incomplete or imprecise. This paper demonstrate designing fully connected neural network system using four different weight calculation algorithms. Input data for weight calculation is constructed in the matrix format based on the pairwise comparison of input constraints. This comparison is performed using saaty’s method. This input matrix helps to build judgment between several individuals, forming a single judgment. Algorithm considered here are Geometric average mean, Linear algebra calculation, Successive matrix squaring method, and analytical hierarchical processing method. Based on the quality parameter of performance, it is observed that analytical hierarchical processing is the most promising mathematical method for finding appropriate weight. Analytical hierarchical processing works on structuration of the problem into sub problems, Hence it the most prominent method for weight calculation in fully connected NN.
ISSN:2074-904X
2074-9058
DOI:10.5815/ijisa.2018.06.08