• Journal of Korea Game Society
• /
• v.14 no.6
• /
• pp.39-48
• /
• 2014

Go is an extremely complex strategy board game despite its simple rules. By using MCTS, the computer Go programs with handicap game have been defeated human Go professionals. MCTS is based on the winning rate estimated by MC simulation rather than strategy concept. Meanwhile Genetic algorithm equipped with an adequate fitness function can find out the best solutions in the game. The game of Tic-Tac-Toe, also known as Naughts and Crosses, is one of the most popular games. We tried to find out the best strategy in the game of Tic-Tac-Toe. The experimental result showed that Genetic algorithm enables to find efficient strategies and can be applied to other board games such as Go and chess.

• Journal of Korea Game Society
• /
• v.16 no.4
• /
• pp.79-86
• /
• 2016

Monte-Carlo Tree Search(MCTS) is a best-first tree search algorithm and has been successfully applied to various games, especially to the game of Go. We evaluate the performance of MCTS playing against each other in the game of Tic-Tac-Toe. It reveals that the first player always has an overwhelming advantage to the second player; and we try to find out the reason why the first player is superior to the second player in spite of the fact that the best game result should be a draw. Since MCTS is a statistical algorithm based on the repeated random sampling, it cannot adequately tackle an urgent problem that needs a strategy, especially for the second player. For this, we propose a strategic MCTS(S-MCTS) and show that the S-MCTS player never loses a Tic-Tac-Toe game.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.49 no.2
• /
• pp.115-122
• /
• 2012

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.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2007.06a
• /
• pp.310-314
• /
• 2007

In this paper, we develop the thinking extension education program for the gifted students of information, and prove the validity and effectiveness of the proposed model by presenting the Tic-tac-toe problem as the practical example of the information-gifted students. This model consists of four phases which has the game tree as data structure and the search of game tree as control structure. And the search of game tree becomes the basis of the thinking extension education program. This model gives the help for students to learn representing the problem as tree structure and solving the problem of tree structure using the search method of game tree. The internal ability of the information-gifted for thinking extension of this education program contains the fluency, perceptiveness, originality, power of concentration, imaginative power, analyzing skills, pattern recognition, space sense, synthesizing, problem-solving.

• Journal of Korea Game Society
• /
• v.14 no.3
• /
• pp.47-54
• /
• 2014

The game of Go is one of the oldest games and originated at least more than 2,500 years ago. In game programming the most successful approach is to use game tree searches using evaluation functions. However it is really difficult to construct feasible evaluation function in computer Go. Monte-Carlo Tree Search(MCTS) has created strong computer Go programs such as MoGo and CrazyStone which defeated human Go professionals played on the $9{\times}9$ board. MCTS is based on the winning rate estimated by Monte-Carlo simulation. Prior to implementing MCTS into computer Go, we tried to measure each winning rate of three positions, center, corner and side, in Tic-Tac-Toe playing as the best first move. The experimental result revealed that the center is the best, a corner the next and a side the last as the best first move.

• Journal of Korea Game Society
• /
• v.15 no.5
• /
• pp.109-118
• /
• 2015

The game of Go originated from ancient China is regarded as one of the most difficult challenges in the filed of AI. Over the past few years, the top computer Go programs based on MCTS have surprisingly beaten professional players with handicap. MCTS is an approach that simulates a random sequence of legal moves until the game is ended, and replaced the traditional knowledge-based approach. We applied the UCT algorithm which is a MCTS variant to the game of Tic-Tac-Toe for finding the best first move, and compared it with the result generated by a pure MCTS. Furthermore, we introduced and compared the performances of epsilon-Greedy algorithm and UCB algorithm for solving the Multi-Armed Bandit problem to understand the UCB.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.11 no.6
• /
• pp.1228-1234
• /
• 2007

In this paper, we develop the thinking extension education program for the gifted students of information and prove the validity and effectiveness of the proposed model by presenting the Tic-tac-toe problem as the practical example of the information-gifted students. This model consists of four phases which has the game tree as data structure and the search of game lee as control structure. And the search of game tree becomes the basis of the thinking extension education program. This model gives the help for students to learn representing the problem as tree structure and solving the problem of tree structure using the search method of game tree. The internal ability of the information-gifted for thinking extension of this education program contains the fluency, perceptiveness, originality, power of concentration, imaginative power, analyzing skills, pattern recognition, space sense, synthesizing, problem-solving.

• Proceedings of the Korean Information Science Society Conference
• /
• 2006.06a
• /
• pp.34-36
• /
• 2006

본 연구는 특정 사물을 계속 접하면서 그 사물에 대한 기억 강도가 의식적 노력 없이도 점점 강화되는 암묵적 기억 인출과정 associative memory retrieval의 DNA 연산 가능성을 논한다. 예를 들어 한 표적 단어에 대한 노출이 이를 관찰하는 시스템에게 그 단어의 기억 강도를 강화시키는 반면, 그와 유사한 다른 단어는 천천히 감소되고 나머지 가장 다른 단어는 일찍 잊혀지는 현상을 생각할 수 있다. 이들 단어들과 알파벳 철자들을 DNA 염기서열로 표현하고 simulated annealing을 통하여 결합 결과를 얻는다. Ridge regression 형태의 supervised 학습을 통하여 한 가지 표적 단어가 많이 생성되도록 DNA 조각들의 개수 분포를 변화시켜 진행한다. 실험 예로 'tic' 'tac' 'toe' 세 가지 단어를 그 아이템으로 정하여 계속 자극받는 표적 단어의 갯수가 증가함을 DNA annealing 시뮬레이션을 통하여 확인할 수 있다. 또한 'tac' 과 't' 와 'c'를 공유하는 'tic' 의 감소 점도가 't'만을 공유하는 'toe' 보다 느림을 확인할 수 있다. 위의 실험들을 통해 연합기억associative memory의 암묵적 인출과정을 분자 층위에서 표현할 수 있음을 확인 할 수 있다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2010.11a
• /
• pp.871-874
• /
• 2010

요즘 다양한 스마트폰의 보급과 함께 스마트폰에서 활용되는 어플리케이션들이 주목 받고 있다. 그 중에 가장 활발히 어플리케이션이 개발되어 등록되어 있는 아이폰의 앱스토어는 개인 개발자들이 자발적으로 앱 개발에 참여할 수 있도록 유도하고 있다. 하지만 Xcode 라는 생소한 개발 툴을 이용하여 MacOS 라는 운영체제에서 개발을 하다 보니, 많은 기존 윈도우 기반의 스마트폰 개발자들이 아이폰 앱을 개발하는데 적지 않은 어려움이 있는 편이다. 본 논문에서는 아이폰에서 블루투스를 이용한 2 인용 대전 게임인 틱택토(Tick-tac-toe)를 C++기반으로 개발하여 그 내용을 소개한다.

• Korean Journal of Cognitive Science
• /
• v.8 no.4
• /
• pp.35-53
• /
• 1997

본 논문은 컴퓨터 시각을 이용하여 제스처를 인식함으로써 사용자에게 보다 편리한 인터페이스를 제공하는 것을 목표로 한다. 제안하는 제스처 인식 방법은 손영역을 획득하는 손영역 획득 모듈？손영역을 인식하는 인식 모듈로 나누어 수행한다. 손영역 획득 모듈에서는 손색상 모델？손색상 결정함수를 정의하여 칼라영상의 영역 분리를 수행하였고, 칼만필터를 이용하여 손색상 모델을 갱신하고 탐색영역을 제한하여 영역 추적을 용이하게 하였다. 영역 추적은 전 시점의 손영역 정보를 이용하여 현 시점의 손영역을 획득한다. 인식 모듈에서는 정적인 제스처를 표현하는 객체 프레임？행동 프레임, 그리고 동적인 제스처를 표현하는 스키마를 정의한다. 그리고 획득된 손영역？정합을 수행함으로써 제스처를 인식한다. 실험 결갬灌？제안하는 제스처 기반 인터페이스를 적용한 삼목(Tic-Tac-Toe) 게임 프로그램을 구현하였다. 사용자는 제스처를 이용하여 컴퓨터와 게임을 진행한다. 제안하는 시스템은 다른 종류의 게임 프로그램이나 마우스의 역할을 수행하는 윈도우 시스템의 제어, 그리고 가상 현실 시스템에 적용될 수 있다.