• Journal of the Korean School Mathematics Society
• /
• v.18 no.2
• /
• pp.223-240
• /
• 2015

This paper deals with how to design and develop white-box based e-learning contents which are equipped with conceptual understanding and step-by-step computational procedures for studying vector calculus for science-engineering majors who might need supplementary mathematics learning. Noting that rewriting rules are often used in school mathematics for students' problem solving, the theoretical aspects of rewriting rules are reviewed for developing supplementary e-learning contents for them. The software design of step-by-step problem solving requires careful arrangement of rewriting rules and pattern matching techniques for white-box procedures using a computer algebra system such as Mathematica. Several modules for step-by-step problem solving as well as producing dynamic display of e-learning contents was coded by Mathematica in order to find the length of a curve in vector calculus after implementing several rules for differentiation and integration. The developed contents are equipped with diagnostic modules and immediate feedback for supplementary learning in terms of a tutorial. At the end, this paper indicates the strengths and features of the developed contents for college students who need to increase math learning capabilities, and suggests future research directions.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2000.11a
• /
• pp.107-110
• /
• 2000

In this paper, we propose a method of constructing neural networks using bio-inspired emergent and evolutionary concepts. This method is algorithm that is based on the characteristics of the biological DNA and growth of plants. Here is, we propose a constructing method to make a DNA coding method for production rule of L-system. L-system is based on so-called the parallel rewriting mechanism. The DNA coding method has no limitation in expressing the production rule of L-system. Evolutionary algorithms motivated by Darwinian natural selection are population based searching methods and the high performance of which is highly dependent on the representation of solution space. In order to verify the effectiveness of our scheme, we apply it to one step ahead prediction of Mackey-Glass time series.

• 제어로봇시스템학회:학술대회논문집
• /
• 2000.10a
• /
• pp.280-280
• /
• 2000

In this paper, we propose a method of constructing equation using bio-inspired emergent and evolutionary concepts. This method is algorithm that is based on the characteristics of the biological DNA and growth of plants. Here is. we propose a constructing method to make a DNA coding method for production rule of L-system. L-system is based on so-called the parallel rewriting mechanism. The DNA coding method has no limitation in expressing the production rule of L-system. Evolutionary algorithms motivated by Darwinian natural selection are population based searching methods and the high performance of which is highly dependent on the representation of solution space. In order to verify the effectiveness of our scheme, we apply it to one step ahead prediction of Mackey-Glass time series.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2000.05a
• /
• pp.224-227
• /
• 2000

In this Paper, we prepose a method of constructing neural networks using bio-inspired emergent and evolutionary concepts. This method is algorithm that is based on the characteristics of the biological DNA and growth of plants. Here is, we propose a constructing method to make a DNA coding method for production rule of L-system. L-system is based on so-called the parallel rewriting mechanism. The DNA coding method has no limitation in expressing the production rule of L-system. Evolutionary algorithms motivated by Darwinian natural selection are population based searching methods and the high performance of which is highly dependent on the representation of solution space. In order to verify the effectiveness of our scheme, we apply it to one step ahead prediction of Mackey-Glass time series, Sun spot data and KOSPI data.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2018.10a
• /
• pp.916-919
• /
• 2018

심층신경망 모델은 우수한 성능을 갖고 있음에도 불구하고 모델이 어떤 판단 과정을 통해 결론을 내렸는지 파악하기 어렵다. 그에 따라 판단에 대한 근거가 중요한 분야에서는 심층신경망 모델을 적용한 실제 사례를 찾기 어렵다. 인공신경망 모델을 해석하기 어렵다는 문제를 해결하기 위해 내부 구조를 이용하여 규칙을 추출하는 decompositional 접근법이 제안되었으나 기존의 연구는 대부분 은닉층이 1개인 다층 퍼셉트론 모델에서 규칙을 생성하는 것을 가정하고 있다. 오늘날 사용하는 심층신경망 모델은 일반적으로 여러 은닉층을 가지고 있기 때문에 기존의 접근법을 그대로 적용할 경우 규칙 불확실성에 따라 잘못된 규칙을 추출하는 문제가 발생한다. 본 논문은 decompositional 접근법에 존재하는 규칙 불확실성 문제를 완화하고 깊이가 깊은 심층신경망 모델에 규칙을 추출하는 방법을 제안한다. 제안한 접근법은 실제 활성화 값을 통해 지식을 추출하며, 이를 통해 규칙 불확실성 문제를 완화할 수 있었다.

• Annual Conference on Human and Language Technology
• /
• 2004.10d
• /
• pp.35-39
• /
• 2004

본 논문은 실용적인 구문분석기의 전단계로서, 자동 구축된 구문패턴사전과 규칙을 이용하여 구묶음하는 방법을 제안한다. 우선 규칙은 구문분석 말뭉치(30,875어절)를 대상으로 자동 추출된 고빈도의 규칙(Rewriting Rule)을 본 논문에 맞게 수동으로 구축하였다. 규칙은 조건부, 행위부로 이루어진 이진 규칙(binary rule)의 형태를 이루며, 명사구(NP), 수식어구(AP, DP), 인용구(X), 용언구(VP, VC)을 대상으로 15개를 구축하였다. 그리고 구문패턴은 중심어와 중심어 선행 요소의 특성뿐만 아니라 중심어 후행 요소도 고려하여 형식화시킨 것으로, 중심어의 복합용언 여부에 따라 일반용언패턴과 본+보조용언패턴으로 구분한다. 부분적인 언어 현상의 처리보다는 실세계에서 사용되는 수많은 문장들에 내재되어 있는 매우 광범위한 언어 현상의 처리를 하기 위해, 구문패턴은 형태소주석 말뭉치(460만 어절)을 대상으로 자동 구축하였다. 구축된 구문패턴사전과 규칙을 이용하여 구묶음을 수행한 결과 정확율 83.09%가 나타났다.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.10 no.4
• /
• pp.315-323
• /
• 2000

In this paper, we propose a method of constructing neural networks using bio-inpired emergent and evolutionary concepts. This method is algorithm that is based on the characteristics of the biological DNA and growth of plants, Here is, we propose a constructing method to make a DNA coding method for production rule of L-system. L-system is based on so-called the parallel rewriting nechanism. The DNA coding method has no limitation in expressing the produlation the rule of L-system. Evolutionary algotithms motivated by Darwinaian natural selection are population based searching methods and the high performance of which is highly dependent on the representation of solution space. In order to verify the effectiveness of our scheme, we apply it one step ahead prediction of Mackey-Glass time series, Sunspot data and KOSPI data.

• Journal of the Korean Society for information Management
• /
• v.14 no.2
• /
• pp.213-234
• /
• 1997

A stemming algorithm for the Korean language free-text retrieval system has been designed and implemented. The algorithm contains three major parts and it operates iteratively ; firstly, stop-words are removed with a use of a stop-word list ; secondly, a basic removing procedure proceeds with a rule table 1, which contains the suffixes, the postpositional particles, and the optionally adopted symbols specifying an each stemming action ; thirdly, an extended stemming and rewriting procedures continue with a rule table 2, which are composed of th suffixes and the optionally combined symbols representing various actions depending upon the context-sensitive rules. A test was carried out to obtain an indication of how successful the algorithm was and to identify any minor changes in the algorithm for an enhanced one. As a result of it, 21.4 % compression is achieved and an error rate is 15.9%.

• The KIPS Transactions:PartA
• /
• v.12A no.5 s.95
• /
• pp.385-390
• /
• 2005

Set constraints logic language is a language that adopts `set theory` in programming. In this paper, we introduce the procedure for solving set constraints proposed by A. Dovier and show how the procedure can be implemented in logic language Prolog. The procedure is represented in `rewriting rules` and this representation is characterized by having nondeterministic rule applicationsand mathematical variables that is difficult to be implemented in general programming languages. In this paper, we show that the representation can be easily implemented by using nondeterministic control, logical variables and data structure `list` provided in Prolog. Our implementation has following advantages.First we have implemented the full features of the language. Second we have described the implementation detail in thisresearch. Third other used the commercial Prolog called SICStus, but we are using CIAO Prolog with GNU GPL(General Public License) and anyone can use it freely. Forth the software of our implementation is open source so anyone can use, modify, and distribute it freely.

• Journal of Korean Association for Spatial Structures
• /
• v.11 no.3
• /
• pp.125-135
• /
• 2011

This study presents the shape creation process using L-system model of morphogenesis technique. In general, L-system model has been applied to represent the visualization of biological plant. But, this study proposes the shape generation process of L-system model to apply the architectural field. The L-system model consists of two parts such as string generation step and string analysis step. The string generation step shows the process for a string rewriting. This step requires alphabet, axiom and rules to generate a string. Also, the string analysis step gives the meaning in string to generate various forms. Especially, through the various application examples, we can find out the shape creation models for the space structures.