• 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.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1998.06a
• /
• pp.399-403
• /
• 1998

In this paper, we proposed a new fuzzy supervised learning algorithm. We construct, and train, a new type fuzzy neural net to model the linear activation function. Properties of our fuzzy neural net include : (1) a proposed linear activation function ; and (2) a modified delta rule for learning algorithm. We applied this proposed learning algorithm to exclusive OR,3 bit parity using benchmark in neural network and pattern recognition problems, a kind of image recognition.

• Journal of the Korean Institute of Telematics and Electronics C
• /
• v.35C no.1
• /
• pp.42-54
• /
• 1998

For decreasing intersymbol interference (ISI) due to band-limited channels in digitalcommunication, the uses of equalization techniques are necessary. Among the useful adaptive equalization techniques, because of their ease of implementation and nonlinear capabilites, the neural networks have been used as an alternative for effectively dealing with the channel distortion. In this paepr, a complex-valued multilayer percepron is proposed as a nonlinear adaptive equalizer. After the important properties that a suitable complex-valued activation function must possess are discussed, a new complex-valued activation function is developed for the proposed schemes to deal with M-ary QAM signals of any constellation sizes. It has been further proven that by the nonlinear transformation of the proposed function, the correlation coefficient between the real and imaginary parts of input data decreases when they are jointly Gaussian random variables. Lastly, the effectiveness of the proposed scheme is demonstrated by simulations. The proposed scheme provides, compared with the linear equalizer using the least mean squares (LMS) algorith, an interesting improvement concerning Bit Error Rate (BER) when channel distortions are nonlinear.

• 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 Institute of Electronics Engineers of Korea CI
• /
• v.49 no.2
• /
• pp.115-122
• /
• 2012

We present here a new class of activation functions for neural networks, which herein will be called CosGauss function. This function is a cosine-modulated gaussian function. In contrast to the sigmoidal-, hyperbolic tangent- and gaussian activation functions, more ridges can be obtained by the CosGauss function. It will be proven that this function can be used to aproximate polynomials and step functions. The CosGauss function was tested with a Cascade-Correlation-Network of the multilayer structure on the Tic-Tac-Toe game and iris plants problems, and results are compared with those obtained with other activation functions.

• The Journal of the Korea Contents Association
• /
• v.9 no.2
• /
• pp.97-105
• /
• 2009

This paper presents a combination of the generalized Cascade Correlation and generalized Recurrent Cascade Correlation learning algorithms. The new network will be able to grow with vertical or horizontal direction and with recurrent or without recurrent units for the quick solution of the pattern classification problem. The proposed algorithm was tested learning capability with the sigmoidal activation function and hyperbolic tangent activation function on the contact lens and balance scale standard benchmark problems. And results are compared with those obtained with Cascade Correlation and Recurrent Cascade Correlation algorithms. By the learning the new network was composed with the minimal number of the created hidden units and shows quick learning speed. Consequently it will be able to improve a learning capability.

• Korean Chemical Engineering Research
• /
• v.48 no.1
• /
• pp.110-115
• /
• 2010

The experiment was designed to compare pyrolysis kinetics of two different classes of imported coal. The pyrolysis behaviors of the coals were first observed with thermogravimetric analyzer(TGA). The kinetic analysis was further done based on a new distributed activation energy model(New DAEM). During the analysis, weight loss curves measured at three different heating rates were used to obtain the activation energy distribution function curve f(E) of a given coal sample where a mean activation energy is determined by its peak. The results show a significant difference in the mean activation energy between two coals for the pyrolytic reaction. The prediction of a chemical percolation devolatilization(CPD) model where the kinetics obtained from the New DAEM method were incorporated is in much closer agreement with an experimental data of TGA particularly for the bituminous coal.

• Smart Structures and Systems
• /
• v.33 no.2
• /
• pp.133-143
• /
• 2024

Piezoelectric (PZT) actuators have been widely used in precision positioning fields for their excellent displacement resolution. However, due to the inherent characteristics of piezoelectric actuators, hysteresis has been proven to greatly reduce positioning performance. In this paper, five mathematical hysteretic models based on activation function are proposed to characterize the nonlinear hysteresis characteristics of piezoelectric actuators. Then the performance of the proposed models is verified by particle swarm optimization (PSO) algorithm and the experiment data. Thirdly, the fitting performance of the proposed models is compared with the classical Bouc-Wen model. Finally, the performance of the five proposed models in modelling hysteresis nonlinearity of piezoelectric drivers is compared, in terms of RMSE, MAPE, SAPE and operation efficiency, and relevant suggestions are given.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.18 no.10
• /
• pp.75-80
• /
• 2017

In this paper, we describe the effect of the regularization method and the network with identity mapping on the performance of the activation functions in deep convolutional neural networks. The activation functions act as nonlinear transformation. In early convolutional neural networks, a sigmoid function was used. To overcome the problem of the existing activation functions such as gradient vanishing, various activation functions were developed such as ReLU, Leaky ReLU, parametric ReLU, and ELU. To solve the overfitting problem, regularization methods such as dropout and batch normalization were developed on the sidelines of the activation functions. Additionally, data augmentation is usually applied to deep learning to avoid overfitting. The activation functions mentioned above have different characteristics, but the new regularization method and the network with identity mapping were validated only using ReLU. Therefore, we have experimentally shown the effect of the regularization method and the network with identity mapping on the performance of the activation functions. Through this analysis, we have presented the tendency of the performance of activation functions according to regularization and identity mapping. These results will reduce the number of training trials to find the best activation function.

• Proceedings of the Korea Concrete Institute Conference
• /
• 2001.05a
• /
• pp.947-952
• /
• 2001

The prediction model is proposed to estimate the variation of compressive strength of fly ash concrete with aging. After analyzing the experimental result with the model, the regression results are presented according to fly ash replacement content and water/cement ratio. Based on the regression results, the influence of fly ash replacement content and water/cement ratio on apparent activation energy was investigated. According to the analysis, the model provides a good estimate of compressive strength development of fly ash concrete with aging. As the fly ash replacement content increases, the limiting relative compressive strength and initial apparent activation energy become greater. The concrete with water/cement ratio smaller than 0.40 shows that the limiting relative compressive strength and apparent activation energy are nearly constant according to water/cement ratio. But, the concrete with water/cement ratio greater than 0.40 has the increasing limiting relative compressive strength and apparent activation energy with increasing water/cement ratio.