scholarly journals Designing Artificial Neural Networks Using Particle Swarm Optimization Algorithms

2015 ◽  
Vol 2015 ◽  
pp. 1-20 ◽  
Author(s):  
Beatriz A. Garro ◽  
Roberto A. Vázquez
Keyword(s):  
Particle Swarm Optimization ◽  
Transfer Functions ◽  
Learning Algorithm ◽  
Optimization Algorithms ◽  
Back Propagation ◽  
Particle Swarm ◽  
Classification Error ◽  
Classification Problems ◽  
Swarm Optimization ◽  
Artificial Neural

Artificial Neural Network (ANN) design is a complex task because its performance depends on the architecture, the selected transfer function, and the learning algorithm used to train the set of synaptic weights. In this paper we present a methodology that automatically designs an ANN using particle swarm optimization algorithms such as Basic Particle Swarm Optimization (PSO), Second Generation of Particle Swarm Optimization (SGPSO), and a New Model of PSO called NMPSO. The aim of these algorithms is to evolve, at the same time, the three principal components of an ANN: the set of synaptic weights, the connections or architecture, and the transfer functions for each neuron. Eight different fitness functions were proposed to evaluate the fitness of each solution and find the best design. These functions are based on the mean square error (MSE) and the classification error (CER) and implement a strategy to avoid overtraining and to reduce the number of connections in the ANN. In addition, the ANN designed with the proposed methodology is compared with those designed manually using the well-known Back-Propagation and Levenberg-Marquardt Learning Algorithms. Finally, the accuracy of the method is tested with different nonlinear pattern classification problems.

Training oscillatory neural networks using natural gradient particle swarm optimization

Robotica ◽  
2014 ◽  
Vol 33 (7) ◽  
pp. 1551-1567 ◽  
Author(s):  
Hamed Shahbazi ◽  
Kamal Jamshidi ◽  
Amir Hasan Monadjemi ◽  
Hafez Eslami Manoochehri
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Particle Swarm Optimization ◽  
Transfer Functions ◽  
Learning Algorithm ◽  
Particle Swarm ◽  
Humanoid Robots ◽  
Unknown Parameters ◽  
Swarm Optimization ◽  
Oscillatory Neural Network

SUMMARYIn this paper, a new design of neural networks is introduced, which is able to generate oscillatory patterns in its output. The oscillatory neural network is used in a biped robot to enable it to learn to walk. The fundamental building block of the neural network proposed in this paper is O-neurons, which can generate oscillations in its transfer functions. O-neurons are connected and coupled with each other in order to shape a network, and their unknown parameters are found by a particle swarm optimization method. The main contribution of this paper is the learning algorithm that can combine natural policy gradient with particle swarm optimization methods. The oscillatory neural network has six outputs that determine set points for proportional-integral-derivative controllers in 6-DOF humanoid robots. Our experiment on the simulated humanoid robot presents smooth and flexible walking.

scholarly journals Modeling and optimizing an electrochemical oxidation process using artificial neural network, genetic algorithm and particle swarm optimization

2018 ◽  
Vol 83 (3) ◽  
pp. 379-390
Author(s):  
Banghai Liu ◽  
Chunji Jin ◽  
Jiteng Wan ◽  
Pengfang Li ◽  
Huanxi Yan
Keyword(s):  
Neural Network ◽  
Genetic Algorithm ◽  
Artificial Neural Network ◽  
Particle Swarm Optimization ◽  
Electrochemical Oxidation ◽  
Back Propagation ◽  
Particle Swarm ◽  
Swarm Optimization ◽  
Operation Conditions ◽  
Artificial Neural

This study proposes a novel hybrid of artificial neural network (ANN), genetic algorithm (GA), and particle swarm optimization (PSO) to model and optimize the relevant parameters of an electrochemical oxidation (EO) Acid Black 2 process. The back propagation neural network (BPNN) was used as a modelling tool. To avoid over-fitting, GA was applied to improve the generalized capability of BPNN by optimizing the weights. In addition, an optimization model was developed to assess the performance of the EO process, where total organic carbon (TOC) removal, mineralization current efficiency (MCE), and the energy consumption per unit of TOC (ECTOC) were considered. The operation conditions of EO were further optimized via PSO. The validation results indicted the proposed method to be a promising method to estimate the efficiency and to optimize the parameters of the EO process.

A MUTATION PARTICLE SWARM OPTIMIZATION ALGORITHM FOR MULTILAYER PERCEPTRON TRAINING WITH APPLICATIONS

2013 ◽  
Vol 09 (01) ◽  
pp. 1350003
Author(s):  
ZENGHAI CHEN ◽  
JING WU ◽  
ZHERU CHI
Keyword(s):  
Particle Swarm Optimization ◽  
Optimization Algorithm ◽  
Multilayer Perceptron ◽  
Back Propagation ◽  
Particle Swarm ◽  
Premature Convergence ◽  
Superior Performance ◽  
Mutation Operator ◽  
Classification Problems ◽  
Swarm Optimization

Particle swarm optimization (PSO), a prevalent optimization algorithm, has been successfully applied to various fields of science and engineering. However, PSO still suffers from some problems such as premature convergence. To solve these problems, we propose a mutation PSO (MPSO) in this paper. Compared with the traditional PSO, there are two main improvements of the proposed MPSO. First, a new particle update rule is explored. The new rule updates a particle's position according to not only its best known position and the global best known position of the swarm, but also a number of other particles' best known positions. The second improvement is that a mutation operator is employed. Mutation operator is used to avoid premature convergence. The MPSO is utilized to train a multilayer perceptron (MLP). The MLP trained by MPSO is finally applied to two classification problems: Iris flower classification and scene classification. For comparison purposes, traditional PSO, genetic algorithm (GA), and back-propagation (BP) are also investigated. Experimental results demonstrate the superior performance of the proposed MPSO for MLP training.

Sign in / Sign up

Export Citation Format

Share Document