AI Chat AI Image Generator AI Video Text to Speech

Using CODEQ to Train Feed-forward Neural Networks

02/03/2010

∙

by Mahamed G. H. Omran, et al.

∙

∙

CODEQ is a new, population-based meta-heuristic algorithm that is a hybrid of concepts from chaotic search, opposition-based learning, differential evolution and quantum mechanics. CODEQ has successfully been used to solve different types of problems (e.g. constrained, integer-programming, engineering) with excellent results. In this paper, CODEQ is used to train feed-forward neural networks. The proposed method is compared with particle swarm optimization and differential evolution algorithms on three data sets with encouraging results.

Mahamed G. H. Omran
1 publication
Faisal al-Adwani
1 publication

research

∙ 06/23/2012

Analysis of a Nature Inspired Firefly Algorithm based Back-propagation Neural Network Training

Optimization algorithms are normally influenced by meta-heuristic approa...

0 Sudarshan Nandy, et al. ∙

research

∙ 02/27/2015

Norm-Based Capacity Control in Neural Networks

We investigate the capacity, convexity and characterization of a general...

0 Behnam Neyshabur, et al. ∙

research

∙ 04/27/2015

Optimal Convergence Rate in Feed Forward Neural Networks using HJB Equation

A control theoretic approach is presented in this paper for both batch a...

0 Vipul Arora, et al. ∙

research

∙ 09/12/2012

Training a Feed-forward Neural Network with Artificial Bee Colony Based Backpropagation Method

Back-propagation algorithm is one of the most widely used and popular te...

0 Sudarshan Nandy, et al. ∙

research

∙ 06/10/2022

An application of neural networks to a problem in knot theory and group theory (untangling braids)

We report on our success on solving the problem of untangling braids up ...

0 Alexei Lisitsa, et al. ∙

research

∙ 02/21/2023

On the Behaviour of Pulsed Qubits and their Application to Feed Forward Networks

In the last two decades, the combination of machine learning and quantum...

0 Matheus Moraes Hammes, et al. ∙

research

∙ 02/19/2002

On model selection and the disability of neural networks to decompose tasks

A neural network with fixed topology can be regarded as a parametrizatio...

0 Marc Toussaint, et al. ∙