• Journal of Korea Multimedia Society
• /
• v.21 no.10
• /
• pp.1142-1149
• /
• 2018

Recently, computer vision application is increasing by using CNN which is one of the deep learning algorithms. However, CNN does not provide perfect classification performance due to gradient vanishing problem. Most of CNN algorithms use an activation function called ReLU to mitigate the gradient vanishing problem. In this study, four activation functions that can replace ReLU were applied to four different structural networks. Experimental results show that ReLU has the lowest performance in accuracy, loss rate, and speed of initial learning convergence from 20 experiments. It is concluded that the optimal activation function varied from network to network but the four activation functions were higher than ReLU.

• Journal of The Korean Society of Agricultural Engineers
• /
• v.63 no.1
• /
• pp.103-116
• /
• 2021

Analysis of runoff is substantial for effective water management in the watershed. Runoff occurs by reaction of a watershed to the rainfall and has non-linearity and uncertainty due to the complex relation of weather and watershed factors. ANN (Artificial Neural Network), which learns from the data, is one of the machine learning technique known as a proper model to interpret non-linear data. The performance of ANN is affected by the ANN's structure, the number of hidden layer nodes, learning rate, and activation function. Especially, the activation function has a role to deliver the information entered and decides the way of making output. Therefore, It is important to apply appropriate activation functions according to the problem to solve. In this paper, ANN models were constructed to estimate runoff with different activation functions and each model was compared and evaluated. Sigmoid, Hyperbolic tangent, ReLU (Rectified Linear Unit), ELU (Exponential Linear Unit) functions were applied to the hidden layer, and Identity, ReLU, Softplus functions applied to the output layer. The statistical parameters including coefficient of determination, NSE (Nash and Sutcliffe Efficiency), NSEln (modified NSE), and PBIAS (Percent BIAS) were utilized to evaluate the ANN models. From the result, applications of Hyperbolic tangent function and ELU function to the hidden layer and Identity function to the output layer show competent performance rather than other functions which demonstrated the function selection in the ANN structure can affect the performance of ANN.

• International journal of advanced smart convergence
• /
• v.6 no.4
• /
• pp.73-79
• /
• 2017

The Convolutional Neural Network (CNN) has shown an excellent performance in computer vision task. Applications of CNN include image classification, object detection in images, autonomous driving, etc. This paper will evaluate the performance of CNN model with ReLU and SELU as activation function. The evaluation will be performed on four different choices of hyperparameter which are initialization method, network configuration, optimization technique, and regularization. We did experiment on each choice of hyperparameter and show how it influences the network convergence and test accuracy. In this experiment, we also discover performance improvement when using SELU as activation function over ReLU.

• The Transactions of the Korean Institute of Electrical Engineers
• /
• v.41 no.3
• /
• pp.274-280
• /
• 1992

In this paper, an Improved Error Back Propagation Algorithm is introduced, which avoids Network Paralysis, one of the problems of the Error Backpropagation learning rule. For this purpose, we analyzed the reason for Network Paralysis and modified the Activation Function Derivative of the standard Error Backpropagation Algorithm which is regarded as the cause of the phenomenon. The characteristics of the modified Activation Function Derivative is analyzed. The performance of the modified Error Backpropagation Algorithm is shown to be better than that of the standard Error Back Propagation algorithm by various experiments.

• Journal of the Korea Society of Computer and Information
• /
• v.11 no.3
• /
• pp.107-115
• /
• 2006

This paper presents a new class of activation functions for Cascade Correlation learning algorithm, which herein will be called CosGauss function. This function is a cosine modulated gaussian function. In contrast to the sigmoidal, hyperbolic tangent and gaussian functions, more ridges can be obtained by the CosGauss function. Because of the ridges, it is quickly convergent and improves a pattern recognition speed. Consequently it will be able to improve a learning capability. This function was tested with a Cascade Correlation Network on the two spirals problem and results are compared with those obtained with other activation functions.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.15 no.3
• /
• pp.1724-1733
• /
• 2014

This paper presents a pattern recognition analysis of two spirals problem and optimization of Cascade Correlation learning algorithm using in combination with a non-monotone function as CosExp(cosine-modulated symmetric exponential function) and a monotone function as sigmoid function. In addition, the algorithm's optimization is attempted. By using genetic algorithms the optimization of the algorithm will attempt. In the first experiment, by using CosExp activation function for candidate neurons of the learning algorithm is analyzed the recognized pattern in input space of the two spirals problem. In the second experiment, CosExp function for output neurons is used. In the third experiment, the sigmoid activation functions with various parameters for candidate neurons in 8 pools and CosExp function for output neurons are used. In the fourth experiment, the parameters are composed of 8 pools and displacement of the sigmoid function to determine the value of the three parameters is obtained using genetic algorithms. The parameter values applied to the sigmoid activation functions for candidate neurons are used. To evaluate the performance of these algorithms, each step of the training input pattern classification shows the shape of the two spirals. In the optimizing process, the number of hidden neurons was reduced from 28 to15, and finally the learning algorithm with 12 hidden neurons was optimized.

• Journal of Institute of Control, Robotics and Systems
• /
• v.3 no.6
• /
• pp.594-601
• /
• 1997

A new algorithm is proposed for training the multilayer perceptrion(MLP) in pattern classification problems to accelerate the learning speed. It is shown that the sigmoid activation function of the output node can have deterimental effect on the performance of learning. To overcome this detrimental effect and to use the information fully in supervised learning, an objective function for binary modes is proposed. This objective function is composed with two new output activation functions which are selectively used depending on desired values of training patterns. The effect of the objective function is analyzed and a training algorithm is proposed based on this. Its performance is tested in several examples. Simulation results show that the performance of the proposed method is better than that of the conventional error back propagation (EBP) method.

• Journal of the Korean Society of Physical Medicine
• /
• v.16 no.1
• /
• pp.111-121
• /
• 2021

PURPOSE: This study examined the effects of core stability exercise on the strength, activation of the trunk muscle, and pulmonary function in a Guillain-Barre syndrome (GBS) patient. METHODS: A 38-year-old male with GBS was enrolled in the study. A core stability exercise program was implemented for four weeks with a duration of 30 min/day and a frequency of three days/week. The program consisted of abdominal crunch, Swiss ball crunch, bicycle crunch, medicine ball sit-up with a toss, medicine ball rotational chest pass, raised upper body and lower body, and dead bug. Measurements of the strength of the trunk muscle (trunk flexion and hip flexion), activation of trunk muscles (rectus femoris; RA, external oblique abdominal; EOA, internal oblique abdominal; IOA, erector spinae; ES), and pulmonary function (forced expiratory capacity; FVC, forced expiratory volume at one second; FEV1) were taken before and after four weeks of core stability exercise. RESULTS: The strength of trunk muscles increased in the trunk and hip flexion after four weeks of core stability exercise, respectively, compared to the baseline levels. Activation of the trunk muscles increased in RA, EOA, and IOA after four weeks of core stability exercise compared to baseline levels, but decreased in ES after four weeks of core stability exercise compared to the baseline levels. The pulmonary function increased in FVC and FEV1 after four weeks of core stability exercise compared to the baseline levels. CONCLUSION: These results suggest that core stability exercise improves strength, Activation of the trunk muscle, And pulmonary function in patients with GBS.

• Honam Mathematical Journal
• /
• v.27 no.2
• /
• pp.225-232
• /
• 2005

We obtain the approximation order to a smooth function on a compact subset of $\mathbb{R}$ by generalized translation networks. In our study, the activation function is infinitely many times continuously differentiable function but it does not have special properties around ${\infty}$ and $-{\infty}$ like a sigmoidal activation function. Using the Jackson's Theorem, we get the approximation order. Especially, we obtain the approximation order by a neural network with a fixed threshold.

• 제어로봇시스템학회:학술대회논문집
• /
• 2000.10a
• /
• pp.20-20
• /
• 2000

Back-propagation neural network (BPNN) is the most prevalently used paradigm in modeling semiconductor manufacturing processes, which as a neuron activation function typically employs a bipolar or unipolar sigmoid function in either hidden and output layers. In this study, applicability of another linear function as a neuron activation function is investigated. The linear function was operated in combination with other sigmoid functions. Comparison revealed that a particular combination, the bipolar sigmoid function in hidden layer and the linear function in output layer, is found to be the best combination that yields the highest prediction accuracy. For BPNN with this combination, predictive performance once again optimized by incrementally adjusting the gradients respective to each function. A total of 121 combinations of gradients were examined and out of them one optimal set was determined. Predictive performance of the corresponding model were compared to non-optimized, revealing that optimized models are more accurate over non-optimized counterparts by an improvement of more than 30%. This demonstrates that the proposed gradient-optimized teaming for BPNN with a linear function in output layer is an effective means to construct plasma models. The plasma modeled is a hemispherical inductively coupled plasma, which was characterized by a 24 full factorial design. To validate models, another eight experiments were conducted. process variables that were varied in the design include source polver, pressure, position of chuck holder and chroline flow rate. Plasma attributes measured using Langmuir probe are electron density, electron temperature, and plasma potential.