Training of artificial neural network using new initialization approach of particle swarm optimization for data classification

A Ashraf, WH Bangyal, HT Rauf… - … Conference on …, 2020 - ieeexplore.ieee.org
… In this paper, a new initialization technique called Adaptive weight PSO with initializing
Another novel variant of PSO trained neural network (NN-PSO) is presented in [11]. This …

A new initialization approach in particle swarm optimization for global optimization problems

WH Bangyal, A Hameed, W Alosaimi… - Computational …, 2021 - Wiley Online Library
… proposed a novel pseudorandom initialization strategy called the … We have compared the
novel techniques with the basic … that the training of neural networks with the WE-PSO algorithm …

Using PSO-GA algorithm for training artificial neural network to forecast solar space heating system parameters

B Jamali, M Rasekh, F Jamadi, R Gandomkar… - Applied Thermal …, 2019 - Elsevier
PSO for optimizing input parameters and the results showed that the suggested novel ANN is
the most efficient method … The algorithm is initialized with n players, half of which will play in …

Artificial neural networks based optimization techniques: A review

…, MA Hannan, R Mohamed, JA Ali, S Mekhilef, A Milad - Electronics, 2021 - mdpi.com
… Input parameters are initialized within the specified range, … different kinds of optimization
techniques such as PSO, EA, CSA, … novel way of solving optimization tasks by the neural network

Training simple recurrent deep artificial neural network for forecasting using particle swarm optimization

E Bas, E Egrioglu, E Kolemen - Granular Computing, 2022 - Springer
… Unfortunately, the training of simple recurrent neural networks is problematic because of …
a new training algorithm based on particle swarm optimization. The algorithm does not use

A review on weight initialization strategies for neural networks

MV Narkhede, PP Bartakke, MS Sutaone - Artificial intelligence review, 2022 - Springer
… , simulated annealing, tabu search methods, particle swarm optimization, genetic algorithm
… weight optimization and weight initialization techniques for non-iterative training have been …

PSO-GA based hybrid with Adam Optimization for ANN training with application in Medical Diagnosis

RK Yadav - Cognitive Systems Research, 2020 - Elsevier
… This paper introduces a novel PSO-GA based hybrid training … Adam Optimization for training
Artificial Neural Networks. We aim … Since the initialization of the weights may play a decisive …

A hybrid metaheuristic method in training artificial neural network for bankruptcy prediction

A Ansari, IS Ahmad, AA Bakar, MR Yaakub - IEEE access, 2020 - ieeexplore.ieee.org
… In this research, random initialization in used for assigning … of the PSO and backpropagation
as neural networks training … layer perceptron NN as a novel training approach to cover the …

Improved chaotic initialization of particle swarm applied to feature selection

H Djellali, N Ghoualmi - 2019 International Conference on …, 2019 - ieeexplore.ieee.org
… , chaotic initialization methods are proposed for PSO applied to … We introduce a novel chaotic
particles swarm optimization (… The training and test phase require respectively 70% and 30…

Hybrid PSO (SGPSO) with the Incorporation of discretization operator for training RBF neural network and optimal feature selection

AK Mahapatra, N Panda, BK Pattanayak - Arabian Journal for Science and …, 2023 - Springer
use of PSO in training artificial neural networks (ANNs), many researchers have castoff this
algorithm as a suitable trainer to train … In this study, the weight vectors are randomly initialized