Comparing backpropagation with a genetic algorithm for neural network training

Gupta, Jatinder N. D.; Sexton, Randall S.

doi:10.1016/s0305-0483(99)00027-4

Cited by 191 publications

(77 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The training phase may consist of several epochs. A popular approach used in the training phase is back-propagation learning; however, researchers have pointed out that some commonly used learning algorithms have disadvantages [10,11]. Several heuristic algorithms, including genetic algorithm (GA) [12], particle swarm optimization (PSO) [13] and ant colony optimization (ACO) [14] have been proposed for the purpose of training neural networks.…”

Section: Introductionmentioning

confidence: 99%

Predicting Student Academic Performance: A Comparison of Two Meta-Heuristic Algorithms Inspired by Cuckoo Birds for Training Neural Networks

2014

View full text Add to dashboard Cite

Predicting student academic performance with a high accuracy facilitates admission decisions and enhances educational services at educational institutions. This raises the need to propose a model that predicts student performance, based on the results of standardized exams, including university entrance exams, high school graduation exams, and other influential factors. In this study, an approach to the problem based on the artificial neural network (ANN) with the two meta-heuristic algorithms inspired by cuckoo birds and their lifestyle, namely, Cuckoo Search (CS) and Cuckoo Optimization Algorithm (COA) is proposed. In particular, we used previous exam results and other factors, such as the location of the student's high school and the student's gender as input variables, and predicted the student academic performance. The standard CS and standard COA were separately utilized to train the feed-forward network for prediction. The algorithms optimized the weights between layers and biases of the neuron network. The simulation results were then discussed and analyzed to investigate the prediction ability of the neural network trained by these two algorithms. The findings demonstrated that both CS and COA have potential in training ANN and ANN-COA obtained slightly better results for predicting student academic performance in this case. It is expected that this work may be used to support student admission procedures and strengthen the service system in educational institutions. OPEN ACCESSAlgorithms 2014, 7 539

show abstract

Section: Introductionmentioning

confidence: 99%

Predicting Student Academic Performance: A Comparison of Two Meta-Heuristic Algorithms Inspired by Cuckoo Birds for Training Neural Networks

2014

View full text Add to dashboard Cite

show abstract

“…However, one limitation of this technique, which is a gradient-descent technique, is that it requires a differentiable neuron transfer function. Also, as neural networks generate complex error surfaces with multiple local minima, the BP tends to converging into local minima instead of a global minimum [4].…”

Section: Introductionmentioning

confidence: 99%

Improved Cuckoo Search Algorithm for Feed forward Neural Network Training

Valian¹,

Mohanna²,

Tavakoli³

2011

IJAIA

201

122

View full text Add to dashboard Cite

show abstract

“…Sankar K. Pal and Dinabandhu Bhandari [1] used binary-coded GA for selection of optimal weights in MLP. Gupta and Sexton [6], Huang and Chang [12] proposed genetic algorithms that outperform significantly than backpropagation in training the MLP. In this paper, we have proposed a real-coded GA for training the weights of a multilayer perceptron.…”

Section: Introductionmentioning

confidence: 99%

Performance Analysis of Neural Networks Training using Real Coded Genetic Algorithm

Sarangi¹,

Majhi²,

Panda³

2012

IJCA

View full text Add to dashboard Cite

Multilayer perceptrons (MLPs) are widely used for pattern classification and regression problems. Backpropagation (BP) algorithm is known technique in the training of multilayer perceptrons. However for its optimum training convergence, the learning and momentum parameters need to be tuned on trial and error method. Further, sometimes the backpropagation algorithm fails to achieve global convergence. To alleviate these problems we suggest a genetic algorithm based training for MLP network. Both binary coded and real coded genetic algorithm are used and a comparative training performance analysis has been studied. It is observed from simulation results that both the schemes outperform backpropagation algorithm and achieve global convergence. Further the real coded GA based training shows a faster convergence than binary coded GA based training. For simulation datasets are taken from UCI based machine learning repository. Hence real-coded genetic algorithm finds an alternative for back propagation based training algorithm.

show abstract

Comparing backpropagation with a genetic algorithm for neural network training

Cited by 191 publications

References 10 publications

Predicting Student Academic Performance: A Comparison of Two Meta-Heuristic Algorithms Inspired by Cuckoo Birds for Training Neural Networks

Predicting Student Academic Performance: A Comparison of Two Meta-Heuristic Algorithms Inspired by Cuckoo Birds for Training Neural Networks

Improved Cuckoo Search Algorithm for Feed forward Neural Network Training

Performance Analysis of Neural Networks Training using Real Coded Genetic Algorithm

Contact Info

Product

Resources

About