• Korean Journal of Cognitive Science
• /
• v.16 no.4
• /
• pp.351-368
• /
• 2005

The manual construction of the knowledge-base takes much time and effort, and it is hard to adjust intelligence systems to dynamic and flexible environment. Thus mental development in those systems has been investigated in recent years. Autonomous mental development is a new paradigm for developing autonomous machines, which are adaptive and flexible to the environment. Learning conversation, a kind of mental development, is an important aspect of conversational agents. In this paper, we propose a learning conversation method for conversational agents which uses several promising techniques; speech-act templates and genetic programming. Knowledge acquisition of conversational agents is implemented by finite state machines and templates, and dynamic sentence generation is implemented by genetic programming Several illustrations and usability tests how the usefulness of the proposed method.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2023.01a
• /
• pp.17-18
• /
• 2023

비지도형 도메인 적응(UDA)에 대한 최근 연구는 도메인 적응에 대한 설명 및 전이 가능한 특징을 풀어 내기 위해 적대적 학습에 의존한다. 그러나 기존 방법에는 대상 도메인의 클래스 인식(class-aware) 정보를 고려하지 않고는 잠재 공간의 구별 가능성을 완전히 보장할 수 없다는 것과 소스 및 대상 도메인의 샘플만으로는 잠재 공간에서 도메인 불변(domain- invariant) 특성을 추출하기에 부족하다는 두 가지 문제가 있다고 알려져 있다. 본 논문에서는 기존 알려진 UDA의 도메인 적응시 발생되는 문제를 해결하기 위해 Adversarial Discriminative Domain Adaptation(ADDA)에서 mixup을 활용해 신경망의 로버스트네스를 향상시키는 것을 확인하였다.

• The KIPS Transactions:PartB
• /
• v.13B no.4 s.107
• /
• pp.421-428
• /
• 2006

Intelligent Tutoring System(ITS), which offers individualized learning environment that consider many learners' variable, is realized by the effective alternative to take the place of domain expert. Accordingly, research on Learning Companion System(LC) is currently noticing. However, to develop LCS which applies effective interaction, it is necessary to combine several LCs, and personalized knowledge base have to be made first. Therefore, in this paper, we propose the 'Knowledge Base Object Medel', which is based on connectionist' in cognition structure, represents learner's knowledge to self-learnig object, and grows adaptive object by proprietor, verify the validity. This model lays the groundwork for design of personalized knowledge base, offers clue to development of adaptive ITS using knowledge base object.

• Journal of KIISE:Computing Practices and Letters
• /
• v.13 no.5
• /
• pp.338-342
• /
• 2007

In this paper we propose a user adaptive post-processing method to improve the accuracy of speaker dependent, isolated word speech recognition, particularly for mobile devices. Our method considers the recognition result of the basic recognizer simply as a high-level speech feature and processes it further for correct recognition result. Our method learns correlation between the output of the basic recognizer and the correct final results and uses it to correct the erroneous output of the basic recognizer. A multi-layer perceptron model is built for each incorrectly recognized word with high frequency. As the result of experiments, we achieved a significant improvement of 41% in recognition accuracy (41% error correction rate).

• Journal of the Korean Institute of Intelligent Systems
• /
• v.6 no.4
• /
• pp.49-60
• /
• 1996

The objective of this paper is to develop an adaptive learning method for fuzzy hypercubes using a neural network. An intelligent control system is proposed by exploiting only the merits of a fuzzy logic controller and a neural network, assuming that we can modify in real time the consequential parts of the rulebase with adaptive learning, and that initial fuzzy control rules are established in a temporarily stable region. We choose the structure of fuzzy hypercubes for the fuzzy controller, and utilize the Perceptron learning rule in order to upda1.e the fuzzy control ru1c:s on-line with the output errors. As a result, the effectiveness and the robustness of this intelligent controller are shown with application of the proposed adaptive fuzzy-neuro controller to control of the cart-pole system.

• Journal of KIISE:Computing Practices and Letters
• /
• v.16 no.5
• /
• pp.601-605
• /
• 2010

In this paper, we propose a GBL(Game Based Learning) content of intelligent tutoring capability. The objective of our GBL content is to learn the Karnaugh Map which is generally used to simplify boolean functions. Our GBL content well-motivates learners with interesting game-based scenarios and also, through an intelligent tutoring module, gives learners adaptive feedbacks such as hints and explanations while maintaining learners' contextual immersion. Additionally, we identified significant improvement in terms of learning effectiveness by analyzing the test results of two (experimental and controlled) student groups learning the Karnaugh Map.

• Proceedings of the Korea Multimedia Society Conference
• /
• 1998.04a
• /
• pp.438-443
• /
• 1998

최근 멀티미디어 응용 기술을 기반한 컴퓨터 교육 매체 개발이 활발히 진행되어 왔다. 본 연구에서 수준별 개별 학습으로 학습 효과를 극대화하기 위한 지능형 멀티미디어 교습 시스템(IMTS)을 제안한다. 제안하는 시스템은 활발한 상호작용으로 학습자의 상태를 진단하고, 개별 학습자 수준을 고려한 동적인 학습 과정을 능동적으로 수립하면서 교습 활동을 전개해 나간다. 제안하는 시스템은 다양한 학습자 수준과 상태에 따른 적응적 교습 과정을 수행하기 위하여 학습자 모델을 유지 관리한다. 그리고 다수의 학습자를 위한 원격 교습 과정을 수행하기 위하여 학습자 모델을 유지 관리한다. 그리고 다수의 학습자를 위한 원격 교습 시스템을 효율적으로 운영하기 위하여 교습 과정에 필요한 모든 모듈을 에이전트로 대체하여 클라이언트/서버 환경에서 교습 활동을 효율적으로 수행하도록 설계하였다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 1999.05a
• /
• pp.370-374
• /
• 1999

The proposed algorithm used the Hybrid teaming rule in the input and hidden layer, and Back-Propagation teaming rule in the hidden and output layer. From the results of simulation of tracking control with one link manipulator as a plant, we verify the usefulness of the proposed control method to compare with common direct adaptive neural network control method; proposed hybrid teaming rule showed faster loaming time faster settling time than the direct adaptive neural network using Back-propagation algorithm. Usefulness of the proposed control method is that it is faster the learning time and settling time than common direct adaptive neural network control method.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.30 no.1
• /
• pp.88-94
• /
• 2019

A leakage canceller and adaptive algorithm for FMCW Radar is presented. Because a strong leakage signal causes various problems in the transceiver and digital processor, specific FMCW radars are in need of a leakage canceller. The leakage canceller has an adaptive structure and the algorithm calculates the prediction vector and learns the adaptive coefficient simultaneously. The proposed algorithm an improvement of 10 dB in the cancellation performance.

• The Journal of Korean Association of Computer Education
• /
• v.6 no.2
• /
• pp.121-135
• /
• 2003

This paper proposes a web-based adaptive tutoring system based on fuzzy set that provides learning materials and questions dynamically according to students' knowledge state, and gives advices for the learning after an evaluation. For this, we design a courseware knowledge structure systematically and then construct a fuzzy level set on the basis of it considering importance of learning targets, difficulty of learning materials and relation degree between learning targets and learning materials. Using the fuzzy level set, our system offers learning materials and questions to adapt to individual students. Moreover, a result of the test is evaluated with fuzzy linguistic variable. Appling the fuzzy concept to the tutoring system could naturally consider and deal with various and uncertain items of learning environment thus could offer more flexible and effective instruction-learning methods.