Journal Article

Artificial neural networks training algorithm integrating invasive weed optimization with differential evolutionary model

Nabipour, Narjes, Movassagh, Ali Akbar, Gheisari, Mehdi, Abbasi, Aaqif Afzaal, Alzubi, Jafar A., Mohan, Senthilkumar, Rahimi, Mohamadtaghi

2023

Overview

Artificial intelligence techniques are excessively used in computing for training, forecasting and evaluation purposes. Among these techniques, artificial neural network (ANN) is widely used for developing prediction models. ANNs use various Meta-heuristic algorithms including approximation methods for training the neural networks. ANN plays a significant role in this area and can be helpful in determining the neural network input coefficient. The main goal of presented study is to train the neural network using meta-heuristic approaches and to enhance the perceptron neural network precision. In this article, we used an integrated algorithm to determine the neural network input coefficients. Later, the proposed algorithm was compared with other algorithms such as ant colony and invasive weed optimization for performance evaluation. The results reveal that the proposed algorithm results in more convergence with neural network coefficient as compared to existing algorithms. However the proposed method resulted in reduction of prediction error in the neural network.

• Publisher: Springer Berlin Heidelberg,Springer Nature B.V
• Subject: Algorithms / Ant colony optimization / Artificial Intelligence / Artificial neural networks / Coefficients / Computational Intelligence / Engineering / Heuristic / Heuristic methods / Network topologies / Neural networks / Optimization algorithms / Original Research / Performance evaluation / Prediction models / Problem solving / Robotics and Automation / User Interfaces and Human Computer Interaction