• Annual Conference on Human and Language Technology
• /
• 2022.10a
• /
• pp.507-511
• /
• 2022

문법 교정 모델은 입력된 텍스트에 존재하는 문법 오류를 탐지하여 이를 문법적으로 옳게 고치는 작업을 수행하며, 학습자에게 더 나은 학습 경험을 제공하기 위해 높은 정확도와 재현율을 필요로 한다. 이를 위해 최근 연구에서는 문단 단위 사전 학습을 완료한 모델을 맞춤법 교정 데이터셋으로 미세 조정하여 사용한다. 하지만 본 연구에서는 기존 사전 학습 방법이 문법 교정에 적합하지 않다고 판단하여 문단 단위 데이터셋을 문장 단위로 나눈 뒤 각 문장에 G2P 노이즈와 편집거리 기반 노이즈를 추가한 데이터셋을 제작하였다. 그리고 문단 단위 사전 학습한 모델에 해당 데이터셋으로 문장 단위 디노이징 사전 학습을 추가했고, 그 결과 성능이 향상되었다. 노이즈 없이 문장 단위로 분할된 데이터셋을 사용하여 디노이징 사전 학습한 모델을 통해 문장 단위 분할의 효과를 검증하고자 했고, 디노이징 사전 학습하지 않은 기존 모델보다 성능이 향상되는 것을 확인하였다. 또한 둘 중 하나의 노이즈만을 사용하여 디노이징 사전 학습한 두 모델의 성능이 큰 차이를 보이지 않는 것을 통해 인공적인 무작위 편집거리 노이즈만을 사용한 모델이 언어학적 지식이 필요한 G2P 노이즈만을 사용한 모델에 필적하는 성능을 보일 수 있다는 것을 확인할 수 있었다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2020.07a
• /
• pp.329-330
• /
• 2020

본 논문에서는 Azure 클라우드 플랫폼의 가상서버 호스팅을 이용해 데이터 수집 환경을 구축하고, Azure에서 제공하는 자동화된 기계학습(Automated Machine Learning, AutoML)을 기반으로 데이터 분석 방법에 관한 연구를 수행했다. 가상 서버 호스팅 환경에 LAMP(Linux, Apache, MySQL, PHP)를 설치하여 데이터 수집환경을 구축했으며, 수집된 데이터를 Azure AutoML에 적용하여 자동화된 기계학습을 수행했다. Azure AutoML은 소모적이고 반복적인 기계학습 모델 개발을 자동화하는 프로세스로써 기계학습 솔루션 구현하는데 시간과 자원(Resource)를 절약할 수 있다. 특히, AutoML은 수집된 데이터를 분류와 회귀 및 예측하는데 있어서 학습점수(Training Score)를 기반으로 보유한 데이터에 가장 적합한 기계학습 모델의 순위를 제공한다. 이는 데이터 분석에 필요한 기계학습 모델을 개발하는데 있어서 개발 초기 단계부터 코드를 설계하지 않아도 되며, 전체 기계학습 시스템을 개발 및 구현하기 전에 모델의 구성과 시스템을 설계해볼 수 있기 때문에 매우 효율적으로 활용될 수 있다. 본 논문에서는 NPU(Neural Processing Unit) 학습에 필요한 데이터 수집 환경에 관한 연구를 수행했으며, Azure AutoML을 기반으로 데이터 분류와 회귀 등 가장 효율적인 알고리즘 선정에 관한 연구를 수행했다.

• The Journal of Korean Association of Computer Education
• /
• v.9 no.3
• /
• pp.121-128
• /
• 2006

This study suggested the new e-learning systems based on agent to provide an adaptable learning. In Semantic Web environment, to develop an ontology and an intelligent agent is essential for an adaptable e-learning systems. Especially, to develop a reasoning engine using analysis of learning content and learners' information can offer an effective e-learning system. Therefore, we developed an applying model to an adaptable e-learning systems and the various ontologies for Semantic Web environment. Moreover, we analyzed and developed ontologies within the framework of learning domain, a learner and interface. Further, we implemented an intelligent e-learning for applying an agent's reasoning. Through this system proposed, we suggested the new e-learning systems model for Semantic Web environment.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.177-179
• /
• 2022

In the Google Deepmind Challenge match, Alphago defeated Korea's Sedol Lee (human) with 4 wins and 1 loss in the Go match. Finally, artificial intelligence is going beyond the use of human intelligence. The Korean government's budget for the Digital New Deal is 9 trillion won in 2022, and an additional 301 types of data construction projects for artificial intelligence learning will be secured. From 2023, the industrial paradigm will change with the use and application of learning of artificial intelligence in all fields of industry. This paper conducts research to utilize artificial intelligence algorithms. Focusing on the analysis and judgment of data in artificial intelligence learning, research on the appropriate target and scope of application of algorithms in artificial intelligence machine learning and deep learning learning is conducted. This study will provide basic data for artificial intelligence in the 4th industrial revolution technology and artificial intelligence robot use in the 5th industrial revolution technology.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.3
• /
• pp.9-17
• /
• 2021

In this paper, an autonomous multi-agent path planning using reinforcement learning for monitoring of infrastructures and resources in a computationally distributed system was proposed. Reinforcement-learning-based multi-agent exploratory system in a distributed node enable to evaluate a cumulative reward every action and to provide the optimized knowledge for next available action repeatedly by learning process according to a learning policy. Here, the proposed methods were presented by (a) approach of dynamics-based motion constraints multi-agent path-planning to reduce smaller agent steps toward the given destination(goal), where these agents are able to geographically explore on the environment with initial random-trials versus optimal-trials, (b) approach using agent sub-goal selection to provide more efficient agent exploration(path-planning) to reach the final destination(goal), and (c) approach of reinforcement learning schemes by using the proposed autonomous and asynchronous triggering of agent exploratory phases.

• Electronics and Telecommunications Trends
• /
• v.34 no.6
• /
• pp.87-99
• /
• 2019

Reinforcement learning is a type of machine learning paradigm that forces agents to repeat the observation-action-reward process to assess and predict the values of possible future action sequences. This allows the agents to incrementally reinforce the desired behavior for a given observation. Thanks to the recent advancements of deep learning, reinforcement learning has evolved into deep reinforcement learning that introduces promising results in various control and optimization domains, such as games, robotics, autonomous vehicles, computing, industrial control, and so on. In addition to this trend, a number of programming libraries have been developed for importing deep reinforcement learning into a variety of applications. In this article, we briefly review and summarize 10 representative deep reinforcement learning libraries and compare them from a development project perspective.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2022.07a
• /
• pp.315-316
• /
• 2022

본 논문은 스마트 인솔의 압력 데이터를 이용하는 컨볼루션 신경망 모델에 해석가능한 인공지능 방법인 Grad-CAM을 적용하는 방법을 제안한다. 학습된 각 모델에 Grad-CAM을 적용하여 모델에서 중요한 역할을 하는 압력센서와 중요하지 않은 압력센서를 알아내는 방법을 제안하고 데이터마다 학습을 진행하고 학습된 모델을 통해 실제로 중요한 압력센서와 그렇지 않은 압력센서에 대해서 알아본다.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.14 no.4
• /
• pp.457-467
• /
• 2004

In this paper, a robot is considered as an agent, a structure of robot is presented which consisted by multi-subagents and they have diverse capacity such as perception, intelligence, action etc., required for robot. Also, subagents are consisted by micro-agent($\mu$agent) charged for elementary action required. The structure of robot control have two sub-agents, the one is behavior based reactive controller and action selection sub agent, and action selection sub-agent select a action based on the high label action and high performance, and which have a learning mechanism based on the reinforcement learning. For presented robot structure, it is easy to give intelligence to each element of action and a new approach of multi robot control. Presented robot is simulated for two goals: chaotic exploration and obstacle avoidance, and fabricated by using 8bit microcontroller, and experimented.

• Journal of the Korea Society of Computer and Information
• /
• v.25 no.12
• /
• pp.93-100
• /
• 2020

This study aims to design and develop effective digital contents to improve the ability for artificial intelligence literacy. First, we defined AI literacy and analyzed the competencies required for artificial intelligence literacy. After selecting the educational elements for AI ability, we composed 10 educational programs. To confirm the appropriateness of designed contents, we verified through content validity test by 10 experts. The CVI value was over 0.75, which was highly valid. The developed content was installed on the online system and applied to 55 AI beginners for 4 weeks. The learners showed a positive result of at least 3.85 in the items of content difficulty, understanding, effectiveness, and learning challenge. As a result of this analysis, we can see that the developed content is positive for helping many people understand AI and improving AI literacy.

• 한국정보교육학회:학술대회논문집
• /
• 2021.08a
• /
• pp.309-314
• /
• 2021

Even though environmental education has been getting more attention along with the recent rapid increase of natural disasters such as heat wave, heavy snow and downpour, it is unlikely for elementary schools to provide actual lessons due to the shortage of financial support and educational resources. This study is designed to enhance the recycling judgement of the elementary students to define paper, glass, plastic, PET, metal by using AI programming. The survey from the student participants shows that the learning and practice with AI programming was positively helpful for more than 70% of the participants in knowledge obtaining and understanding of recycling. The participants also gained better understanding on artificial intelligence and got motivated to have more opportunities to learn artificial intelligence programming.