http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
- 中文 을 입력하시려면 zhongwen을 입력하시고 space를누르시면됩니다.
- 北京 을 입력하시려면 beijing을 입력하시고 space를 누르시면 됩니다.
- 검색키워드
- 저자 : 권기택 (검색결과 33 건)
- 무료
- 기관 내 무료
- 유료
-
-
權奇澤 동양대학교 1996 동양대학교 논문집 Vol.2 No.1
This paper examines the ability of fuzzy neural networks to the approximate realization of fuzzy if-then rules. Fuzzy neural networks in this paper are characterized by fuzzy weights and fuzzy biases. This means that the weights and biases are given by fuzzy numbers instead of real numbers. First, the input-output relation of a three-layer feedforward fuzzy neural network is defined for fuzzy input vectors by the extension principle of Zadeh. Next, a cost function is defined for the level sets of fuzzy actual outputs and fuzzy target outputs. A learning algorithm is derived from the cost function in a similar manner as the back-propagation algorithm. Last, using a numerical example, the fuzzy neural networks with fuzzy weights and fuzzy biases are compared with other fuzzy neural networks with crisp weights and crisp biases designed for handling fuzzy input-output data.
-
권기택 동양대학교 2000 동양대학교 논문집 Vol.6 No.1
This paper propose a stock price prediction system using neural networks. First, an architecture of neural networks is shown. The neural network maps input vectors to target output. A cost function is defined using the output from the neural networks and the corresponding target output. A learning algorithm is derived from the cost function. Next, the standard back-propagation algorithm is applied to the stock price prediction. Last, the proposed stock price prediction system is demonstrated by computer simulations.
-
권기택 동양대학교 1999 동양대학교 논문집 Vol.5 No.1
A neural network-based classification system is constructed to handle incomplete data with missing attribute values, and applied to a medical diagnosis. In this paper, unknown values are represented by intervals. Therefore incomplete data with missing attribute values are transformed into interval data. A learning algorithm for multi-class classification problems of interval input vectors is derived. The proposed approach is applied to the medical diagnosis of hepatic diseases, and its performance is compared with that of a rule-based fuzzy classification system.
-
-
권기택,배철수 한국통신학회 1996 한국통신학회논문지 Vol.21 No.8
This paper proposes four approaches for approximately realizing nonlinear mappling of interval vectors by neural networks. In the proposed approaches, training data for the learning of neural networks are the paris of interval input vectors and interval target output vectors. The first approach is a direct application of the standard BP (Back-Propagation) algorithm with a pre-processed training data. The second approach is an application of the two BP algorithms. The third approach is an extension of the BP algorithm to the case of interval input-output data. The last approach is an extension of the third approach to neural network with interval weights and interval biases. These approaches are compared with one another by computer simulations.
-
-
-
-
고전파 이후의 양식적 고찰 : 피아노 작품을 중심으로 With a Focus on Piano Works
권기택 한국음악학회 1985 한국음악학회논문집 음악연구 Vol.4 No.1
The piano, outstanding as a unique instrument for its harmonic and melodic capacity is thoroughly utilized in performance mediums such as solo, concerto, as well as accompaniment. In other words, because independently, the piano has the capacity to express voluminously in the execution of parts, its practical usage is wide. Even today, the piano can be regarded the most broadly used among instruments. Because of the special distinctive characteristics of the piano, piano music has continued to penetrate and develop through every period up to the present day based upon many varied styles and techniques. Following the techniques of the Classical school, when making stylistic consideration, are generally three period divisions of the then current representative works (e.g. the Romantic, Impressionistic and Modern periods). In the future, whatever the direction of music, the music of the world will continue to captivate as the mutual relationship of line and color capable of entering the center of music; the logical flow, contrast, and subtle melodic movements are vibrantly vivid in the imprint of sound.
DBpia연관 검색어 추천
이 검색어로 많이 본 자료
활용도 높은 자료
