• Journal of Practical Engineering Education
• /
• v.13 no.2
• /
• pp.233-242
• /
• 2021

In this paper, as a liberal arts course for non-majors, we proposed a supervised learning artificial neural network parameter optimization method and a basic education method for activation function to design a basic artificial neural network subject curriculum. For this, a method of finding a parameter optimization solution in a spreadsheet without programming was applied. Through this training method, you can focus on the basic principles of artificial neural network operation and implementation. And, it is possible to increase the interest and educational effect of non-majors through the visualized data of the spreadsheet. The proposed contents consisted of artificial neurons with sigmoid and ReLU activation functions, supervised learning data generation, supervised learning artificial neural network configuration and parameter optimization, supervised learning artificial neural network implementation and performance analysis using spreadsheets, and education satisfaction analysis. In this paper, considering the optimization of negative parameters for the sigmoid neural network and the ReLU neuron artificial neural network, we propose a training method for the four performance analysis results on the parameter optimization of the artificial neural network, and conduct a training satisfaction analysis.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.57 no.11
• /
• pp.2095-2101
• /
• 2008

In this paper, we consider a performance improvement of neural network for predicting defect size of steam generator tube using early stopping. Usually, neural network is trained until MSE becomes less than a prescribed error goal. The smaller the error goal, the greater the prediction performance for the trained data. However, as the error goal is decreased, an over fitting is likely to start during supervised training of a neural network, which usually deteriorates the generalization performance. We propose that, for the prediction of an axisymmetric defect size, early stopping can be used to avoid the over-fitting. Through various experiments on the axisymmetric defect samples, we found that the difference bet ween the prediction error of neural network based on early stopping and that of ideal neural network is reasonably small. This indicates that the error goal used for neural network training for the prediction of defect size can be efficiently selected by early stopping.

• 제어로봇시스템학회:학술대회논문집
• /
• 2005.06a
• /
• pp.2521-2525
• /
• 2005

In this paper, we presented a predictive control technique, which is based on wavelet neural network (WNN), for the control of chaotic systems whose precise mathematical models are not available. The WNN is motivated by both the multilayer feedforward neural network definition and wavelet decomposition. The wavelet theory improves the convergence of neural network. In order to design predictive controller effectively, the WNN is used as the predictor whose parameters are tuned by error between the output of actual plant and the output of WNN. Also the training method for the finding a good WNN model is the Extended Kalman algorithm which updates network parameters to converge to the reference signal during a few iterations. The benefit of EKF training method is that the WNN model can have better accuracy for the unknown plant. Finally, through computer simulations, we confirmed the performance of the proposed control method.

• Journal of Intelligence and Information Systems
• /
• v.5 no.1
• /
• pp.95-101
• /
• 1999

In this paper, a comparison between different methods to combine predictions from neural networks will be given. These methods are bagging, bumping, and balancing. Those are based on the analysis of the ensemble generalization error into an ambiguity term and a term incorporating generalization performances of individual networks. Neural Networks and AI machine learning models are prone to overfitting. A strategy to prevent a neural network from overfitting, is to stop training in early stage of the learning process. The complete data set is spilt up into a training set and a validation set. Training is stopped when the error on the validation set starts increasing. The stability of the networks is highly dependent on the division in training and validation set, and also on the random initial weights and the chosen minimization procedure. This causes early stopped networks to be rather unstable: a small change in the data or different initial conditions can produce large changes in the prediction. Therefore, it is advisable to apply the same procedure several times starting from different initial weights. This technique is often referred to as training ensembles of neural networks. In this paper, we presented a comparison of three statistical methods to prevent overfitting of neural network.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.31B no.1
• /
• pp.88-98
• /
• 1994

A new neural network architecture called the Parallel. Self-Organizing Hierarchical Neural Network (PSHNN) is presented. The new architecture involves a number of stages in which each stage can be a particular neural network (SNN). The experiments performed in comparison to multi-layered network with backpropagation training and indicated the superiority of the new architecture in the sense of classification accuracy, training time,parallelism.

• 제어로봇시스템학회:학술대회논문집
• /
• 1993.10a
• /
• pp.619-623
• /
• 1993

In this paper, a neural network is appled to design a lateral autopilot for airplanes. Linearized lateral dynamics is used in training the neural network controller and verifying the performance as well. To train the neural network, back propagation algorithm is used. In this training, no information about the dynamics to be controlled except sign and rough magnitude of control derivatives is needed. It is shown by computer simulations that the performance and stability margin are satisfactory.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.2 no.1
• /
• pp.15-19
• /
• 2002

Automatic detection of interstitial lung disease using Neural Network is presented. The rounded opacities in the pneumoconiosis X-ray photo are picked up quickly by a back propagation (BP) neural network with several typical training patterns. The training patterns from 0.6 mm ${\O}$ to 4.0 mm ${\O}$ are made by simple circles. The total evaluation is done from the size and figure categorization. Mary simulation examples show that the proposed method gives much reliable result than traditional ones.

• Proceedings of the Computational Structural Engineering Institute Conference
• /
• 2002.10a
• /
• pp.321-329
• /
• 2002

Artificial neural network has been used for damage assessment by many researchers, but there are still some barriers that must be overcome to improve its accuracy and efficiency. The major problems with the conventional neural network are the necessity of many training patterns for neural network teaming process and ambiguity in the relationship of neural network structure to the convergence of solution. In this paper, the PNN is used as a pattern classifier to detect the damages of the railway bridge using dynamic response. The comparison between the mode shape and the natural frequency of structure as training pattern is investigated for approriate selection of the training pattern in the damage detection of railway bridge using the PNN.

• Journal of The Korean Association of Information Education
• /
• v.25 no.5
• /
• pp.791-801
• /
• 2021

In this paper, an educational case that can be applied as artificial intelligence literacy education for preservice teachers and incumbent teachers was studied. To this end, a case of educating the operating principle of an artificial neural network that recognizes images is proposed. This training case focuses on the basic principles of artificial neural network operation and implementation, and applies the method of finding parameter optimization solutions required for artificial neural network implementation in a spreadsheet. In this paper, we focused on the artificial neural network of supervised learning method. First, as an artificial neural network principle education case, an artificial neural network education case for recognizing two types of images was proposed. Second, as an artificial neural network extension education case, an artificial neural network education case for recognizing three types of images was proposed. Finally, the results of analyzing artificial neural network training cases and training satisfaction analysis results are presented. Through the proposed training case, it is possible to learn about the operation principle of artificial neural networks, the method of writing training data, the number of parameter calculations executed according to the amount of training data, and parameter optimization. The results of the education satisfaction survey for preservice teachers and incumbent teachers showed a positive response result of over 70% for each survey item, indicating high class application suitability.

• Journal of Practical Engineering Education
• /
• v.15 no.2
• /
• pp.381-388
• /
• 2023

Through artificial neural network education using spreadsheets, non-major undergraduate students can understand the operation principle of artificial neural networks and develop their own artificial neural network software. Here, training of the operation principle of artificial neural networks starts with the generation of training data and the assignment of correct answer labels. Then, the output value calculated from the firing and activation function of the artificial neuron, the parameters of the input layer, hidden layer, and output layer is learned. Finally, learning the process of calculating the error between the correct label of each initially defined training data and the output value calculated by the artificial neural network, and learning the process of calculating the parameters of the input layer, hidden layer, and output layer that minimize the total sum of squared errors. Training on the operation principles of artificial neural networks using a spreadsheet was conducted for undergraduate non-major students. And image training data and basic artificial neural network development results were collected. In this paper, we analyzed the results of collecting two types of training data and the corresponding artificial neural network SW with small 12-pixel images, and presented methods and execution results of using the collected training data for Orange machine learning model learning and analysis tools.