An Optimal Design Method for Artificial Neural Networks by Using the Design of Experiments

Inohira, Eiichi; Yokoi, Hideki

doi:10.20965/jaciii.2007.p0593

Cited by 10 publications

(10 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…3,4 Our basic idea is that DOE is applied to the problem of an optimal design for MLPs. We show a fl ow chart of our proposed method using the DOE in Fig.…”

Section: Doe-based Optimal Design Methodsmentioning

confidence: 99%

Evaluation of an optimal design method for a multilayer perceptron by using the design of experiments

Inohira

Yokoi

2011

Artif Life Robotics

Self Cite

View full text Add to dashboard Cite

Evaluation of an optimal design method for a multilayer perceptron by using the design of experiments rithm. However, the learning algorithm is a unique factor. Another factor is the design of the MLP. Before training, the number of layers, the numbers of neurons in the hidden layers, and the training conditions such as the learning rates are determined. Trial-and-error and brute-force approaches, and network construction and pruning are all used as conventional design methods. It is diffi cult to apply these methods to MLPs with many layers because the space needed for their design parameters becomes huge. Another problem is that the approximate accuracy of MLPs with the same design parameters has variations due to the use of random numbers for the initial values of the connection weights. We need a design method which includes statistical analysis for MLPs.In previous work 3,4 we proposed a design method using the design of experiments (DOE), 5 which features effi cient experiments with an orthogonal array and quantitative analysis with analysis of variance (ANOVA). We demonstrated that an optimal design of fi ve-layer MLPs could be obtained using our design method. However, there is a problem in evaluating the proposed design method. The problem is a quantitative comparison between the proposed design method and other design methods. It is clear that the proposed designed method is better than trail-and-error or brute-force approaches. We focused on a genetic algorithmbased design method, which is a nonlinear optimization technique, and is expected to be as effi cient as the proposed method.Here, we evaluate the performance of the proposed design method through a comparison with a genetic algorithm-based design method. We target an optimal design of MLPs with six layers. When we deal with a few design parameters, the difference between the proposed design method and other methods is small. Our previous work implied that the accuracy of MLPs with more layers would become higher for the same training data. Therefore, we focus on MLPs with six layers. Moreover, we evaluate the proposed designed method in terms of calculating the amount of optimization. We use various types of training data because the performance of a trained MLP depends on the training data. We refer to the UCI machine learning Abstract We evaluated the performance of an optimal design method for a multilayer perceptron (MLP) by using the design of experiments (DOE). In our previous work, we proposed an optimal design method for MLPs in order to determine the optimal values of such parameters as the number of neurons in the hidden layers and the learning rates. In this article, we evaluate the performance of the proposed design method through a comparison with a genetic algorithm (GA)-based design method. We target an optimal design of MLPs with six layers. We also evaluate the proposed designed method in terms of calculating the amount of optimization. Through the above-mentioned evaluation and analysis, we aim at improving the proposed design ...

show abstract

“…3,4 Our basic idea is that DOE is applied to the problem of an optimal design for MLPs. We show a fl ow chart of our proposed method using the DOE in Fig.…”

Section: Doe-based Optimal Design Methodsmentioning

confidence: 99%

Evaluation of an optimal design method for a multilayer perceptron by using the design of experiments

Inohira

Yokoi

2011

Artif Life Robotics

Self Cite

View full text Add to dashboard Cite

show abstract

“…An optimized ANN [41] is designed which is divided into two stages: experimental condition setup and optimization as shown in fig. 1.…”

Section: B An Optimal Design Of Neural Networkmentioning

confidence: 99%

“…An optimized ANN [41] consists of: a general neural network scans all possible network topologies on given number of nodes for reliability measures then a specialized neural network for highly reliable network design is considered [33][34][35][36][37][38][39][40][41][42][43][44][45]. Both neural networks with fixed and varying link reliabilities are studied [33][34][35][36][37][38]41].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A computational study on the design of overall reliability measures of optimized ANN for computer networks with fixed and varying link reliabilities

Kaushik¹,

Kaur²,

Kohli

2010

2010 IEEE International Conference on Computational Intelligence and Computing Research

View full text Add to dashboard Cite

This paper presents a computational study on the performance of reliability measures by using optimized ANN for computer networks with fixed and varying link reliabilities. This objective of this paper is to focus on the design of minimum cost reliable computer networks when a set of nodes, their topology, and links are given to connect them. A comparative study of various approaches for evaluating reliabilities has been studied such as Monte Carlo simulation methods and upper and lower bounds to bound reliability. The network design problem is difficult when overall reliability measure is considered through these methods. For optimal network design, an optimized ANN is used. ANN is constructed, trained and validated using topologies, with fixed and varying links, and upper-bound on reliability as inputs to produce overall reliability as output. The optimal design of ANN shows that the reliability of growing networks can be measured efficiently.

show abstract

“…In this paper, we used DoE to find the best setting of the ANN parameters in order to achieve a minimum error in force estimation. The applications of DoE techniques to optimize the ANN parameters have been reported in the literature [13][14][15][16][17][18]. It has been found that some factors such as the number of neurons in the hidden layers, transfer function, and training function have significant effects on the ANN performance.…”

Section: Introductionmentioning

confidence: 99%

Application of statistical techniques and artificial neural network to estimate force from sEMG signals

Khoshdel

Akbarzadeh

2016

JAIDM

View full text Add to dashboard Cite

This paper presents an application of the design of experiment(DoE) techniques to determine the optimized parameters of the artificial neural network (ANN)model, which are used to estimate the force from the electromyogram (sEMG) signals. The accuracy of the ANN model is highly dependent on the network parameter settings. There are plenty of algorithms that are used to obtain the optimal ANN settings. However, to the best of our knowledge, no regression analysis has yet been used to model the effect of each parameter as well as presenting the percent contribution and significance level of the ANN parameters for force estimation. In this paper, the sEMG experimental data is collected, and the ANN parameters are regulated based on an orthogonal array design table to train the ANN model. The Taguchi method helps us to find the optimal parameters settings. The analysis of variance (ANOVA) technique is then used to obtain the significance level as well as the contribution percentage of each parameter I order to optimize ANN' modeling in the human force estimation. The results obtained indicate that DoE is a promising solution to estimate the human force from the sEMG signals.

show abstract

An Optimal Design Method for Artificial Neural Networks by Using the Design of Experiments

Cited by 10 publications

References 14 publications

Evaluation of an optimal design method for a multilayer perceptron by using the design of experiments

Evaluation of an optimal design method for a multilayer perceptron by using the design of experiments

A computational study on the design of overall reliability measures of optimized ANN for computer networks with fixed and varying link reliabilities

Application of statistical techniques and artificial neural network to estimate force from sEMG signals

Contact Info

Product

Resources

About