코사인 모듈화 된 가우스 활성화 함수를 사용한 캐스케이드 코릴레이션 학습 알고리즘의 성능 향상

이상화(Sang-Wha Lee),송해상(Hae-Sang Song) 한국컴퓨터정보학회 2006 韓國컴퓨터情報學會論文誌 Vol.11 No.3

본 논문에서는 캐스케이드 코릴레이션 학습 알고리즘을 위한 새로운 클래스의 활성화 함수를 소개한다. 이 함수는 코사인으로 모듈화된 가우스 함수로서 편의상 이 활성화 함수를 코스가우스(CosGauss) 함수라고 칭하기로 한다. 이 함수는 기존의 시그모이드 함수(sigmoidal function), 하이퍼볼릭탄젠트 함수(hyperbolic tangent function), 가우스 함수(gaussian function)에 비해서 등성이(ridge)를 더 많이 얻을 수 있다. 이러한 등성이들로 인하여 빠른 속도로 수렴하고 패턴인식 속도를 향상 시켜서 학습 능력을 향상시킬 수 있다. 캐스케이드 코릴레이션 네트워크에 이 활성화 함수를 사용하여 중요한 기준 문제(benchmark problem)의 하나인 이중나선 문제(two spirals problem)에 대하여 실험하여 다른 활성화 함수들과 결과 값을 비교하였다. 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.

[멀티미디어] 뉴로 네트워크에서 코사인 모듈화 된 가우스함수의 다항식과 계단함수의 근사

이상화(Sangwha Lee) 大韓電子工學會 2012 電子工學會論文誌-CI (Computer and Information) Vol.49 No.2

본 논문에서는 CosGauss라고 하는 코사인함수로 모듈화 된 가우시안 활성화함수가 뉴로 네트워크에서 다항식과 계단함수의 근사에 사용될 수 있음을 증명한다. CosGauss 함수는 시그모이드, 하이퍼볼릭 탄젠트, 가우시안 활성화 함수보다 더 많은 범프(bump)를 구성 할 수 있다. 이 함수를 캐스케이드 코릴레이션 뉴로 네트워크 학습에 사용하여 벤치마크 문제인 Tic-Tac-Toe 게임과 아이리스(iris) 식물 문제와 실험하고 여기에서 얻어진 결과를 다른 활성화 함수를 사용한 결과와 비교 분석한다. 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.

Optimal approximation by one Gaussian function to probability density functions

김광일,조승연,전두배 영남수학회 2023 East Asian mathematical journal Vol.39 No.5

In this paper, we introduce the optimal approximation by a Gaussian function for a probability density function. We show that the ap- proximation can be obtained by solving a non-linear system of parameters of Gaussian function. Then, to understand the non-normality of the em- pirical distributions observed in financial markets, we consider the nearly Gaussian function that consists of an optimally approximated Gaussian function and a small periodically oscillating density function. We show that, depending on the parameters of the oscillation, the nearly Gaussian functions can have fairly thick heavy tails.

Determination of the Distribution of the Preisach Density Function With Optimization Algorithm

Hong Sun-Ki,Koh Chang Seop The Korean Institute of Electrical Engineers 2005 KIEE International Transactions on Electrical Mach Vol.b5 No.3

The Preisach model needs a distribution function or Everett function to simulate the hysteresis phenomena. To obtain these functions, many experimental data obtained from the first order transition curves are usually required. In this paper, a simple procedure to determine the Preisach density function using the Gaussian distribution function and genetic algorithm is proposed. The Preisach density function for the interaction field axis is known to have Gaussian distribution. To determine the density and distribution, genetic algorithm is adopted to decide the Gaussian parameters. With this method, just basic data like the initial magnetization curve or saturation curves are enough to get the agreeable density function. The results are compared with experimental data and we got good agreements comparing the simulation results with the experiment ones.

The smooth topology optimization for bi-dimensional functionally graded structures using level set-based radial basis functions

Wonsik Jung,Thanh T. Banh,Nam G. Luu,Dongkyu Lee 국제구조공학회 2023 Steel and Composite Structures, An International J Vol.47 No.5

This paper proposes an efficient approach for the structural topology optimization of bi-directional functionally graded structures by incorporating popular radial basis functions (RBFs) into an implicit level set (ILS) method. Compared to traditional element density-based methods, a level set (LS) description of material boundaries produces a smoother boundary description of the design. The paper develops RBF implicit modeling with multiquadric (MQ) splines, thin-plate spline (TPS), exponential spline (ES), and Gaussians (GS) to define the ILS function with high accuracy and smoothness. The optimization problem is formulated by considering RBF-based nodal densities as design variables and minimizing the compliance objective function. A LS-RBF optimization method is proposed to transform a Hamilton-Jacobi partial differential equation (PDE) into a system of coupled non-linear ordinary differential equations (ODEs) over the entire design domain using a collocation formulation of the method of lines design variables. The paper presents detailed mathematical expressions for BiDFG beams topology optimization with two different material models: continuum functionally graded (CFG) and mechanical functionally graded (MFG). Several numerical examples are presented to verify the method's efficiency, reliability, and success in accuracy, convergence speed, and insensitivity to initial designs in the topology optimization of two-dimensional (2D) structures. Overall, the paper presents a novel and efficient approach to topology optimization that can handle bi-directional functionally graded structures with complex geometries.

Approximation for the Two-Dimensional Gaussian Q-Function and Its Applications

Jinah Park,Seungkeun Park 한국전자통신연구원 2010 ETRI Journal Vol.32 No.1

In this letter, we present a new approximation for the two-dimensional (2-D) Gaussian Q-function. The result is represented by only the one-dimensional (1-D) Gaussian Q-function. Unlike the previous 1-D Gaussian-type approximation, the presented approximation can be applied to compute the 2-D Gaussian Q-function with large correlations.

이변량 Gaussian 분포함수를 적용한 CFRP 적층 평판의 보강섬유 물성저하 규명

김규동 ( Gyu-dong Kim ),이상열 ( Sang-youl Lee ) 한국복합재료학회 2016 Composites research Vol.29 No.5

본 연구는 이변량 Gaussian 분포함수를 적용하여 CFRP 적층판의 섬유물성 변화를 추정하는 방법을 제안하였다. 섬유의 손상 분포를 규명하기 위하여 수정된 이변량 Gaussian 분포함수를 적용하여 5개의 미지 변수가 고려되었다. 조합된 컴퓨터 기법을 적용하여 역문제를 해결하기 위하여 본 연구에서는 몇 개의 고유진동수와 모드정보를 입력데이터로 활용하였다. 수치해석 예제는 제안된 기법이 적층배열 변화에 따른 CFRP 판의 섬유 손상분포 및 위치를 규명할 수 있는 적합하고 실용적은 방법임을 보여준다. This paper presents a method to detect the fiber property variation of laminated CFRP plates using the bivariate Gaussian distribution function. Five unknown parameters are considered to determine the fiber damage distribution, which is a modified form of the bivariate Gaussian distribution function. To solve the inverse problem using the combined computational method, this study uses several natural frequencies and mode shapes in a structure as the measured data. The numerical examples show that the proposed technique is a feasible and practical method which can prove the location of a damaged region as well as inspect the distribution of deteriorated stiffness of CFRP plates for different fiber angles and layup sequences.

Estimating Suitable Probability Distribution Function for Multimodal Traffic Distribution Function

Yoo, Sang-Lok,Jeong, Jae-Yong,Yim, Jeong-Bin The Korean Society of Marine Environment and safet 2015 海洋環境安全學會誌 Vol.21 No.3

The purpose of this study is to find suitable probability distribution function of complex distribution data like multimodal. Normal distribution is broadly used to assume probability distribution function. However, complex distribution data like multimodal are very hard to be estimated by using normal distribution function only, and there might be errors when other distribution functions including normal distribution function are used. In this study, we experimented to find fit probability distribution function in multimodal area, by using AIS(Automatic Identification System) observation data gathered in Mokpo port for a year of 2013. By using chi-squared statistic, gaussian mixture model(GMM) is the fittest model rather than other distribution functions, such as extreme value, generalized extreme value, logistic, and normal distribution. GMM was found to the fit model regard to multimodal data of maritime traffic flow distribution. Probability density function for collision probability and traffic flow distribution will be calculated much precisely in the future.

Estimating Suitable Probability Distribution Function for Multimodal Traffic Distribution Function

유상록,정재용,임정빈 해양환경안전학회 2015 海洋環境安全學會誌 Vol.21 No.3

The purpose of this study is to find suitable probability distribution function of complex distribution data like multimodal. Normal distribution is broadly used to assume probability distribution function. However, complex distribution data like multimodal are very hard to be estimated by using normal distribution function only, and there might be errors when other distribution functions including normal distribution function are used. In this study, we experimented to find fit probability distribution function in multimodal area, by using AIS(Automatic Identification System) observation data gathered in Mokpo port for a year of 2013. By using chi-squared statistic, gaussian mixture model(GMM) is the fittest model rather than other distribution functions, such as extreme value, generalized extreme value, logistic, and normal distribution. GMM was found to the fit model regard to multimodal data of maritime traffic flow distribution. Probability density function for collision probability and traffic flow distribution will be calculated much precisely in the future.

Estimating Suitable Probability Distribution Function for Multimodal Traffic Distribution Function

Sang-Lok Yoo,Jae-Yong Jeong,Jeong-Bin Yim 해양환경안전학회 2015 海洋環境安全學會誌 Vol.21 No.3

The purpose of this study is to find suitable probability distribution function of complex distribution data like multimodal. Normal distribution is broadly used to assume probability distribution function. However, complex distribution data like multimodal are very hard to be estimated by using normal distribution function only, and there might be errors when other distribution functions including normal distribution function are used. In this study, we experimented to find fit probability distribution function in multimodal area, by using AIS(Automatic Identification System) observation data gathered in Mokpo port for a year of 2013. By using chi-squared statistic, gaussian mixture model(GMM) is the fittest model rather than other distribution functions, such as extreme value, generalized extreme value, logistic, and normal distribution. GMM was found to the fit model regard to multimodal data of maritime traffic flow distribution. Probability density function for collision probability and traffic flow distribution will be calculated much precisely in the future.