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.
RISS 인기검색어
- 검색키워드
- 저자 : 정낙우 (검색결과 8 건)
- 무료
- 기관 내 무료
- 유료
-
정낙우 서강정보대학 1996 論文集 Vol.15 No.-
In the result of industrial development, largeness and highness of techniques, a large amount of information is being treated every year. Achive informationization, we must store in computer, all informations written on paper for a long time and be able to utilize the output value in right time and place. There is recurrent neural network as a model reusing the output value in learning neural network for characters recognition. But most of these methods are not so effectively applied to it. This study suggests a new type of recurrent neural network to classify effectively the static patterns such as off-line handwritten characters. This study shows that this new type is better than those of before in recognizing, the patterns, such as figures and handwritten characters, by using the new J-E(Jordan-Elman) neural network model in which enlarges and Combines Jordan and Elman Model.
-
-
정낙우 서강정보대학 1993 論文集 Vol.12 No.-
The objective of this paper is to implement and compare the neural network method with the conventional techniques such as ststistical method and structural analysis technique for recognizing Hangul characters. Neural network approach turns out to be very reasonable through a comparison with ststistical classifier and analysis of generalization capability. Further works are the modification of proposed networks for recoognizing the multi-font, multi-size characters, and the combination of neural nerwork, approach with conventional recognition methods for better performances.
-
鄭樂宇 서강정보대학 1995 論文集 Vol.14 No.-
The Bayesian "evidence" approximation has recently been employed to determine the noise and weight-penalty terms used in back-propagation. This paper shows that for neural nets it is far easier to use the exact result than it is to use the evidence approximation. Moreover, unlike the evidence approximation, the exact result neither has to be re-calculated for every new 데이타 set, nor requires the running of computer code. This paper also discuses sufficiency conditions for the evidence approximation to hold, why it can sometimes give "resonable" result, etc.
-
鄭樂宇 서강전문대학 1994 論文集 Vol.13 No.-
In this paper, we compare and analyze capabilities of MFA, another algorithms using graph partitioning. The MFA algorithm exhibits the rapid convergence of the neural network while preserving the solution quality afforded by the simulated annealing(SA). The speed of MFA is much faster and is like neural networks; continous average of the discrete degress of freedom are used in the computations, and thes relaxation to their equilibrium values at given temperature much faster than the corresponding Markov Chain employed in simulated annealing. The rate of convergence of MFA on graph partitioning problems is 10 to 100 times of that of the another algorithms.
-
정낙우 서강정보대학 1991 論文集 Vol.10 No.-
This study is considered whether the dynamic reconfigurable dispersive management system can be formed or not by applying. "message oriented mechanism" or "data-gram" method which is transmitted to each message without prior establishment of communication route in the message communication method between process affiliated with different "groups". This paper presents a program abstraction so that autonomous processes, interacting on a resource to provide related service.
-
정낙우(Chung Nak Woo),김병기(Kim Byung Gi) 한국정보처리학회 1997 정보처리학회논문지 Vol.4 No.2
Human gets almost all of his knowledge from the recognition and the accumulation of input patterns, image or sound, that he gets through his eyes and through his car. Among these means, his character recognition, an ability that allows him to recognize characters and understand their meanings through visual information, is now applied to a pattern recognition system using neural network in computer. Recurrent neural network is one of those models that reuse the output value in neural network learning. Recently many studies try to apply this recurrent neural network to the classification of static patterns like off-line handwritten characters. But most of their efforts are not so effective until now. This study suggests a new type of recurrent neural network for an effective classification of the static patterns such as off-line handwritten characters. Using the new J-E(Jordan-Elman) neural network model that enlarges and combines Jordan Model and Elman Model, this paper shows that this new type is better than those of before in recognizing the static patterns such as figures and handwritten characters.
-
KISS연관 검색어 추천
이 검색어로 많이 본 자료
활용도 높은 자료
