Tuning the Structure and Parameters of a Neural Network by Using Cooperative Quantum Particle Swarm Algorithm

2011 ◽  
Vol 48-49 ◽  
pp. 1328-1332 ◽  
Author(s):  
Qi Feng Tang ◽  
Liang Zhao ◽  
Rong Bin Qi ◽  
Hui Cheng ◽  
Feng Qian
Keyword(s):  
Neural Network ◽  
Particle Swarm ◽  
Pso Algorithm ◽  
Particle Swarm Algorithm ◽  
Training Algorithms ◽  
Approximation Accuracy ◽  
Quantum Genetic Algorithm ◽  
Cooperation Mechanism ◽  
Swarm Algorithm ◽  
Redundant Structure

In this paper, a cooperative quantum genetic algorithm-particle swarm algorithm (CQGAPSO) is applied to tune both structure and parameters of a feedforward neural network (NN) simultaneously. In CQGAPSO algorithm, QGA is used to optimize the network structure and PSO algorithm is employed to search the parameters space. The amplitude-based coding method and cooperation mechanism improve the learning efficiency, approximation accuracy and generalization of NN. Furthermore, the ill effects of approximation ability caused by redundant structure of NN are eliminated by CQGAPSO. The experimental results show that the proposed method has better prediction accuracy and robustness in forecasting the sunspot numbers problems than other training algorithms in the literatures.

Integration Particle Swarm Algorithm and its Application in Neural Network

2014 ◽  
Vol 543-547 ◽  
pp. 2133-2136
Author(s):  
Jun Pan ◽  
Xu Cao
Keyword(s):  
Neural Network ◽  
Particle Swarm ◽  
Pso Algorithm ◽  
Particle Swarm Algorithm ◽  
Algorithm Optimization ◽  
Bp Network ◽  
Node Number ◽  
The Neural Network ◽  
Swarm Algorithm ◽  
Hidden Layer

This paper puts forward a kind of evolutionary algorithm and the neural network combining with the new method of optimization of hidden layer nodes number of particle swarm algorithm of neural network. The BP neural network technology is a kind of more mature neural network method, but there are easy to fall into local minimum value, unable to accurately determine the number of hidden layer nodes of the network, the disadvantages such as slow convergence speed. This paper puts forward the optimization with hidden node number of particle swarm neural network (HPSO neural network) is the hidden layer of BP network node number as a particle swarm optimization (PSO) algorithm is an important optimization goal, network of hidden layer nodes and the number of each BP network weights and closed value together, common as particle swarm algorithm optimization goal.

A Quantum-Behaved Particle Swarm Algorithm Combined with Chaotic Mutation

2012 ◽  
Vol 605-607 ◽  
pp. 2442-2446
Author(s):  
Xin Ran Li ◽  
Yan Xia Jin
Keyword(s):  
Particle Swarm ◽  
Pso Algorithm ◽  
Particle Swarm Algorithm ◽  
Local Optimum ◽  
Convergence Problem ◽  
Early Maturity ◽  
Classical Function ◽  
Function Test ◽  
Quantum Behavior ◽  
Swarm Algorithm

The article puts forward an improved PSO algorithm based on the quantum behavior——CMQPSO algorithm to improve premature convergence problem in particle swarm algorithm. The new algorithm first adopts Tent mapping initialization of particle swarm, searches each particle chaos, and strengthens the diversity of searching. Secondly, a method of effective judgment of early stagnation is embedded in the algorithm. Once the early maturity is retrieved, the algorithm mutates particles to jump out of the local optimum particle according to the structure mutation so as to reduce invalid iteration. The calculation of classical function test shows that the improved algorithm is superior to classical PSO algorithm and quantum-behaved PSO algorithm.

scholarly journals Application of Strongly Constrained Space Particle Swarm Optimization to Optimal Operation of a Reservoir System

2018 ◽  
Vol 10 (12) ◽  
pp. 4445 ◽  
Author(s):  
Lejun Ma ◽  
Huan Wang ◽  
Baohong Lu ◽  
Changjun Qi
Keyword(s):  
Particle Swarm Optimization ◽  
Computational Efficiency ◽  
Particle Swarm ◽  
Pso Algorithm ◽  
Optimal Operation ◽  
Computational Time ◽  
Particle Swarm Algorithm ◽  
Swarm Optimization ◽  
Swarm Algorithm ◽  
Low Efficiency

In view of the low efficiency of the particle swarm algorithm under multiple constraints of reservoir optimal operation, this paper introduces a particle swarm algorithm based on strongly constrained space. In the process of particle optimization, the algorithm eliminates the infeasible region that violates the water balance in order to reduce the influence of the unfeasible region on the particle evolution. In order to verify the effectiveness of the algorithm, it is applied to the calculation of reservoir optimal operation. Finally, this method is compared with the calculation results of the dynamic programming (DP) and particle swarm optimization (PSO) algorithm. The results show that: (1) the average computational time of strongly constrained particle swarm optimization (SCPSO) can be thought of as the same as the PSO algorithm and lesser than the DP algorithm under similar optimal value; and (2) the SCPSO algorithm has good performance in terms of finding near-optimal solutions, computational efficiency, and stability of optimization results. SCPSO not only improves the efficiency of particle evolution, but also avoids excessive improvement and affects the computational efficiency of the algorithm, which provides a convenient way for particle swarm optimization in reservoir optimal operation.

PSO Algorithm Based on Perception Range and Application in the Constrained Optimization

2013 ◽  
Vol 380-384 ◽  
pp. 1294-1297
Author(s):  
Hong Xia Liu
Keyword(s):  
Constrained Optimization ◽  
Particle Swarm ◽  
Pso Algorithm ◽  
Extreme Value ◽  
Particle Swarm Algorithm ◽  
Local Minima ◽  
Swarm Optimization ◽  
Scattered Particle ◽  
Glowworm Swarm Optimization ◽  
Swarm Algorithm

There is a shortcoming that particle swarm algorithm is ease fall into local minima. To avoid this drawback, this paper insert into a perception range that from Glowworm swarm optimization. according to domain to determine a perception range, within the scope of perception of all the particles find an extreme value point sequence. All the particles that in the perception scope find a extreme value point sequence, which apply roulette method, in order to choose a particle instead of global extreme value. So as to scattered particle, and avoid the local minima.

Sign in / Sign up

Export Citation Format

Share Document