Genetic Random Weight Change Algorithm for the Learning of Multilayer Neural Networks

06/05/2019
by   Mohammad Ibraim Sarker, et al.
0

A new method to improve the performance of Random weight change (RWC) algorithm based on a simple genetic algorithm, namely, Genetic random weight change (GRWC) is proposed. It is to find the optimal values of global minima via learning. In contrast to Random Weight Change (RWC), GRWC contains an effective optimization procedure which are good at exploring a large and complex space in an intellectual strategies influenced by the GA/RWC synergy. By implementing our simple GA in RWC we achieve an astounding accuracy of finding global minima.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/05/2019

Optimizing method for Neural Network based on Genetic Random Weight Change Learning Algorithm

Random weight change (RWC) algorithm is extremely component and robust f...
research
05/30/2011

Predicting the Structure of Alloys using Genetic Algorithms

We discuss a novel genetic algorithm that can be used to find global min...
research
11/20/2020

An Intelligent System for Spam Detection and Identification of the most Relevant Features based on Evolutionary Random Weight Networks

With the incremental use of e-mails as an essential and popular communic...
research
10/09/2020

Genetic-algorithm-optimized neural networks for gravitational wave classification

Gravitational-wave detection strategies are based on a signal analysis t...
research
12/16/2020

Distributed Global Optimization (DGO)

A new technique of global optimization and its applications in particula...
research
02/02/2022

Flipping the switch on local exploration: Genetic Algorithms with Reversals

One important feature of complex systems are problem domains that have m...
research
11/17/2017

A Genetic Algorithm-Based Solver for Very Large Jigsaw Puzzles

In this paper we propose the first effective automated, genetic algorith...

Please sign up or login with your details

Forgot password? Click here to reset