A hybrid particle swarm optimization–back-propagation algorithm for feedforward neural network training

Zhang, Jingru; Zhang, Jun; Lok, Tat-Ming; Lyu, Michael R.

doi:10.1016/j.amc.2006.07.025

Cited by 566 publications

(287 citation statements)

References 18 publications

Supporting

Mentioning

281

Contrasting

Unclassified

Order By: Relevance

“…Hence, they are advantageous in comparison to an EA-based algorithm that needs to simulated mutation and crossover operators for real-valued weight vector [110]. It was found that PSO guides a population of the FNN weight vectors towards an optimum population [161,162]. Hence, many researchers resorted to working on swarm based metaheuristics for the FNN optimization.…”

Section: Weight Optimizationmentioning

confidence: 99%

See 1 more Smart Citation

Metaheuristic design of feedforward neural networks: A review of two decades of research

Ojha

Abraham

Snel

2017

Engineering Applications of Artificial Intelligence

457

154

View full text Add to dashboard Cite

Over the past two decades, the feedforward neural network (FNN) optimization has been a key interest among the researchers and practitioners of multiple disciplines. The FNN optimization is often viewed from the various perspectives: the optimization of weights, network architecture, activation nodes, learning parameters, learning environment, etc. Researchers adopted such different viewpoints mainly to improve the FNN's generalization ability. The gradient-descent algorithm such as backpropagation has been widely applied to optimize the FNNs. Its success is evident from the FNN's application to numerous real-world problems. However, due to the limitations of the gradient-based optimization methods, the metaheuristic algorithms including the evolutionary algorithms, swarm intelligence, etc., are still being widely explored by the researchers aiming to obtain generalized FNN for a given problem. This article attempts to summarize a broad spectrum of FNN optimization methodologies including conventional and metaheuristic approaches. This article also tries to connect various research directions emerged out of the FNN optimization practices, such as evolving neural network (NN), cooperative coevolution NN, complex-valued NN, deep learning, extreme learning machine, quantum NN, etc. Additionally, it provides interesting research challenges for future research to cope-up with the present information processing era.

show abstract

Section: Weight Optimizationmentioning

confidence: 99%

“…For example, the effectiveness of global (GA) and local search (BP) combination is explained in [127,128]. Similarly, a hybrid PSO and BP algorithms for optimizing FNN were found useful in obtaining better approximation than using one of them alone [129].…”

Section: Hybrid and Memetic Algorithmsmentioning

confidence: 99%

Metaheuristic design of feedforward neural networks: A review of two decades of research

Ojha

Abraham

Snel

2017

Engineering Applications of Artificial Intelligence

457

154

View full text Add to dashboard Cite

show abstract

“…To overcome the drawback of BPNN, in [9] gray wolf optimizer (GWO) is hybrid to the BPNN. Moreover, the PSO algorithm is hybrid to FFNN to optimize the weight value [10]. To improve the predication accuracy, here we hybrid these two popular algorithm to select better connections to the network and the performance of the optimized network are to be measured in predicting future rainfall in a historical dataset.…”

Section: Introductionmentioning

confidence: 99%

Efficient Dissemination of Rainfall Forecasting to Safeguard Farmers from Crop Failure Using Optimized Neural Network Model

Ananthanarayanan¹,

Balan²,

Balamurali³

et al. 2017

IJIES

View full text Add to dashboard Cite

Abstract:In the field of weather forecasting, especially in rainfall prediction many researchers employed different data mining techniques. There is numerous method of organizing agricultural engineering substance and it remains an open research issue particularly when taking to distinctive arrangements of clients -farmers, agricultural engineers, agri-organizations -both from proficiency point of view. Keeping these factors Indian farmers in mind, we have chosen to do research on efficient dissemination of rainfall forecasting to safeguard farmers from crop failure using optimized neural network (NN) model. Here, at first, we generate the feature matrix based on five feature indicator. Once the feature matrix is formed, the prediction is done based on the hybrid classifier. In hybrid classifier, particle swarm optimization algorithm is combined with Grey Wolf optimization for training the RBF NN. The performance of the algorithm is analyzed with the help of real datasets gathered from pechiparai and perunchani regions.

show abstract

“…Currently, there have been many algorithms used to train the ANNs, such as back propagation (BP) algorithm, Levenberg-Marquadt(LM), Quasi-Newton(QN), genetic algorithm (GA), simulating annealing (SA) algorithm, particle swarm optimization (PSO) algorithm, hybrid PSO-BP algorithm [3], hybrid ABC-BP algorithm [4] and so on. Back propagation (BP) learning can realize the training of feed-forward multilayer neural network.…”

Section: Introductionmentioning

confidence: 99%

Training Artificial Neural Network Using Modification of Differential Evolution Algorithm

Bui¹,

Hasegawa²

2015

IJMLC

View full text Add to dashboard Cite

Abstract-Training an artificial neural network (ANN) is an optimization task where the result is to find optimal weight and bias set of the network. There are many traditional method to training ANN, such as Back Propagation (BP) Algorithm, Levenberg-Marquadt (LM), Quasi-Newton (QN), Genetic Algorithm(GA) etc. Traditional training algorithms might get stuck in local minima and the global search techniques might catch global minima very slow. Recently differential evolution (DE) algorithm has been used in many practical cases and has demonstrated good convergence properties. In DE algorithm there are some parameters, which are kept fix throughout the entire evolution process. However we have to tune value of these control parameters and it is not easy to do. Therefore this research we apply the improvement of self-adaptive strategy for controlling parameters in differential evolution algorithm (ISADE-ANN) for training neural network. Experiment results show that the new algorithm ISADE-ANN has higher precision and better performance than traditional training algorithms.Index Terms-Neural network training, differential evolution, global search, local search, multi-peak problems.

show abstract

A hybrid particle swarm optimization–back-propagation algorithm for feedforward neural network training

Cited by 566 publications

References 18 publications

Metaheuristic design of feedforward neural networks: A review of two decades of research

Metaheuristic design of feedforward neural networks: A review of two decades of research

Efficient Dissemination of Rainfall Forecasting to Safeguard Farmers from Crop Failure Using Optimized Neural Network Model

Training Artificial Neural Network Using Modification of Differential Evolution Algorithm

Contact Info

Product

Resources

About