• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• 제20권1호
• /
• pp.155-161
• /
• 2020

In general, optimization problems are difficult to solve simply. The reason is that the given problem is solved as soon as it is simple, but the more complex it is, the very large number of cases. This study is about the optimization of AI neural network. What we are dealing with here is the relief method for constructing AI network. The main topics deal with non-deterministic issues such as the stability and unstability of the overall network state, cost down and energy down. For this one, we discuss associative memory models, that is, a method in which local minimum memory information does not select fake information. The simulated annealing, this is a method of estimating the direction with the lowest possible value and combining it with the previous one to modify it to a lower value. And nonlinear planning problems, it is a method of checking and correcting the input / output by applying the appropriate gradient descent method to minimize the very large number of objective functions. This research suggests a useful approach to relief method as a theoretical approach to solving optimization problems. Therefore, this research will be a good proposal to apply efficiently when constructing a new AI neural network.

• Knowledge Management Research
• /
• 제19권1호
• /
• pp.97-118
• /
• 2018

The finance-investment industry is currently focusing on research related to artificial intelligence and big data, moving beyond conventional theories of financial engineering. However, the case of equity optimization portfolio by using an artificial intelligence, big data, and its performance is rarely realized in practice. Thus, the purpose of this study is to propose process improvements in equity selection, information analysis, and portfolio composition, and lastly an improvement in portfolio returns, with the case of an equity optimization model based on quantitative research by an artificial intelligence. This paper is an empirical study of the portfolio based on an artificial intelligence technology of "D" asset management, which is the largest domestic active-quant-fiduciary management in accordance with the purpose of this paper. This study will apply artificial intelligence to finance, analyzing financial and demand-supply information and automating factor-selection and weight of equity through machine learning based on the artificial neural network. Also, the learning the process for the composition of portfolio optimization and its performance by applying genetic algorithms to models will be documented. This study posits a model that the asset management industry can achieve, with continuous and stable excess performance, low costs and high efficiency in the process of investment.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 한국퍼지및지능시스템학회 2004년도 추계학술대회 학술발표 논문집 제14권 제2호
• /
• pp.433-436
• /
• 2004

In this paper, we introduce a new Fuzzy Polynomial Neural Networks (FPNNS)-like structure whose neuron is based on the Fuzzy Set-based Fuzzy Inference System (FS-FIS) and is different from that of FPNNS based on the Fuzzy relation-based Fuzzy Inference System (FR-FIS) and discuss the ability of the new FPNNS-like structure named Fuzzy Set-based Polynomial Neural Networks (FSPNN). The premise parts of their fuzzy rules are not identical, while the consequent parts of the both Networks (such as FPNN and FSPNN) are identical. This difference results from the angle of a viewpoint of partition of input space of system. In other word, from a point of view of FS-FIS, the input variables are mutually independent under input space of system, while from a viewpoint of FR-FIS they are related each other. The proposed design procedure for networks architecture involves the selection of appropriate nodes with specific local characteristics such as the number of input variables, the order of the polynomial that is constant, linear, quadratic, or modified quadratic functions being viewed as the consequent part of fuzzy rules, and a collection of the specific subset of input variables. On the parameter optimization phase, we adopt Information Granulation (IC) based on HCM clustering algorithm and a standard least square method-based learning. Through the consecutive process of such structural and parametric optimization, an optimized and flexible fuzzy neural network is generated in a dynamic fashion. To evaluate the performance of the genetically optimized FSPNN (gFSPNN), the model is experimented with using the time series dataset of gas furnace process.

• The Transactions of the Korea Information Processing Society
• /
• 제6권5호
• /
• pp.1393-1402
• /
• 1999

This paper proposes an efficient principal feature extraction of the image data using neural networks of a new learning algorithm. The proposed learning algorithm is a backpropagation(BP) algorithm based on the steepest descent and dynamic tunneling. The BP algorithm based on the steepest descent is applied for high-speed optimization, and the BP algorithm based on the dynamic tunneling is also applied for global optimization. Converging to the local minimum by the BP algorithm of steepest descent, the new initial weights for escaping the local minimum is estimated by the BP algorithm of dynamic tunneling. The proposed algorithm has been applied to the 3 image data of 12${\times}$12pixels and the Lenna image of 128${\times}$128 pixels respectively. The simulation results shows that the proposed algorithm has better performances of the convergence and the feature extraction, in comparison with those using the Sanger method and the Foldiak method for single-layer neural networks and the BP algorithm for multilayer neural network.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2002년도 ICCAS
• /
• pp.102.1-102
• /
• 2002

In this paper, we propose Self-organizing neurofuzzy networks(SONFN) and discuss their comprehensive design methodology. The proposed SONFN is generated from the mutually combined structure of both neurofuzzy networks (NFN) and polynomial neural networks(PNN) for model identification of complex and nonlinear systems. NFN contributes to the formation of the premise part of the SONFN. The consequence part of the SONFN is designed using PNN. The parameters of the membership functions, learning rates and momentum coefficients are adjusted with the use of genetic optimization. We discuss two kinds of SONFN architectures and propose a comprehensive learning algorithm. It is shown that this network...

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 한국정밀공학회 2004년도 춘계학술대회 논문요약집
• /
• pp.216-216
• /
• 2004

본 논문은 우리가 일상 생활에서 접하는 에어컨의 핵심 부품인 열 교환기의 제작과정 중에서 확관 공정에서의 확관속도 최적화에 관한 것이다 여기서 열 교환기는 구멍 뚫린 박판형태의 방열핀과 이 구멍을 통과하는 구리재질의 관인 헤어핀의 2가지 주요 부품으로 구성되어있다 그리고 확관기(Fig. 1)에 있어서의 확관공정은 Fig. 2에서 보는 바와 같이 소성변형을 통한 관의 반지름 방향의 팽창으로 방열핀과 헤어핀을 결합시켜주는 높은 정밀도를 요구하는 작업이다.(중략)

• Proceedings of the KIEE Conference
• /
• 대한전기학회 2002년도 하계학술대회 논문집 D
• /
• pp.2749-2751
• /
• 2002

일반화된 회귀 신경망 (GRNN)을 이용하여 플라즈마을 분류하는 새로운 알고리즘을 보고한다. 데이터분포를 통계적인 평균치와 표준편차를 이용하여 특징지었으며, 바이어스 인자을 이용하여 9 종류의 데이터을 발생하였다. 각 데이터에 대하여 GRNN의 학습인자를 최적화하였으며, 모델성능은 예측과 분류 정확도로 나누어 바이어스와 학습인자의 함수로 분석하였다. 바이어스는 모델성능에 상당한 영향을 주었으며, 학습인자와의 상호작용을 통하여 완전 분류를 이루었다.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 한국퍼지및지능시스템학회 1998년도 추계학술대회 학술발표 논문집
• /
• pp.374-378
• /
• 1998

신경망은 복잡하게 나타나는 비선형성을 가지는 실제의 다양한 문제들에 적용이 가능할 뿐만 아니라, 정보들이 가중치에 분산되어 저장됨으로서 강인성을 가지고 있다. 그러나 전방향 다층 신경망 구조를 학습할 수 있는 역전파 알고리즘은 초기 가중치의 영향에 의하여 학습된 결과가 지역 최소점에 빠지기 쉬운 경향이 있다. 본 논문에서는 이러한 문제점을 해결하기 위한 한가지 방법으로서 유전자 알고리즘을 이용하여 전방향 다층 신경망의 가중치를 학습하여, 지역 최소점에 빠지지 않고 학습이 이루어짐을 보인다.

• IE interfaces
• /
• 제8권3호
• /
• pp.231-239
• /
• 1995

일반적으로 공정설계자는 실제 절삭을 위하여 각 공정의 표준 절삭조건에 대하여 적적한 보정을 수행한다. 이러한 보정과정에서 사용되는 지식은 경험에 바탕을 둔 것이므로 이의 시스템화는 경험 지향적인 방법론(Experience-Oriented Method)을 요구한다. 본 논문에서는 밀링 공정을 대상으로, 검색된 표준 절삭조건에 대하여 최적의 절삭조건을 결정하기 위한 방법과 제안된 방법에 의해 개발된 시스템을 소개한다.

• Proceedings of the KIEE Conference
• /
• 대한전기학회 1999년도 하계학술대회 논문집 G
• /
• pp.2959-2961
• /
• 1999

A position control algorithm for a inverted pendulum is studied. The proposed algorithm is based on a fuzzy theory and Generalized Radial Basis Function(GRBF). The conventional fuzzy methods need expert's knowledges or human experiences. The GRBF, which is an optimization algorithm, tunes automatically the input-output membership parameters and fuzzy rules. The simulation is presented to illustrate the approaches.