• 한국컴퓨터정보학회논문지
• /
• 제29권4호
• /
• pp.9-21
• /
• 2024

최근 딥러닝 분야가 빠르게 발전하는 가운데, 다양한 영역에서 거대 언어 모델을 활용하기 위한 많은 연구들이 진행되고 있다. 하지만 언어 모델의 개발 및 활용을 위해서는 방대한 데이터와 고성능 자원이 필요하다는 현실적인 어려움이 존재한다. 이에 따라 프롬프트를 활용하여 언어 모델을 효율적으로 학습할 수 있는 문맥 내 학습이 등장하였지만, 학습에 효과적인 프롬프트가 무엇인지에 대한 명확한 기준은 구체적으로 제시되지 않았다. 이에 본 연구에서는 문맥 내 학습 방법 중 하나인 PET 기법을 활용하여 기존 데이터의 문맥과 유사한 PVP를 선정하고, 이를 통해 생성한 프롬프트를 학습하여 모델의 성능을 향상시킬 수 있는 프롬프트 기반 학습 성능 향상 방법론을 제안한다. 제안 방법론의 성능 평가를 위해 온라인 비즈니스 리뷰 플랫폼인 Yelp에서 수집된 레스토랑 리뷰 데이터 30,100개로 실험을 수행한 결과, 제안 방법론이 기존의 PET 방법론에 비해 정확도와 안정성, 그리고 학습 효율성의 모든 측면에서 우수한 성능을 보임을 확인하였다.

• 한국정보과학회 언어공학연구회:학술대회논문집(한글 및 한국어 정보처리)
• /
• 한국정보과학회언어공학연구회 2022년도 제34회 한글 및 한국어 정보처리 학술대회
• /
• pp.47-52
• /
• 2022

환자와 주변인들에게 다양한 문제를 야기하는 치매와 조현병 진단을 위한 모델을 제안한다. 치매와 조현병 진단을 위해 프로토콜에 따라 녹음한 의사와 내담자 음성 시료를 전사 작업하여 분류 태스크를 수행하였다. 사전 학습한 언어 모델의 MLM Head를 이용해 분류 태스크를 수행하는 Prompt 기반의 분류 모델을 제안하였다. 또한 많은 수의 데이터 수를 확보하기 어려운 의료 분야에 효율적인 Few-Shot 학습 방식을 이용하였다. CLS 토큰을 미세조정하는 일반적 학습 방식의 Baseline과 비교해 Full-Shot 실험에서 7개 태스크 중 1개 태스크에서 macro, micro-F1 점수 모두 향상되었고, 3개 태스크에서 하나의 F1 점수만 향샹된 것을 확인 하였다. 반면, Few-Shot 실험에서는 7개 태스크 중 2개 태스크에서 macro, micro-F1 점수가 모두 향상되었고, 2개 태스크에서 하나의 F1 점수만 향상되었다.

• 한국지능시스템학회논문지
• /
• 제5권3호
• /
• pp.3-10
• /
• 1995

This paper proposedan on-line learning controller which can be applied to nonlinear systems. The proposed on-line learning controller is based on the universal approximation by the local affine mapping-based neural networks. It has self-organizing and learning capability to adapt itself to the new environment arising from the variation of operating point of the nonlinear system. Since the learning controller retains the knowledge of trained dynamics, it can promptly adapt itself to situations similar to the previously experienced one. This prompt adaptability of the proposed control system is illustrated through simulations.

• 인지과학
• /
• 제14권3호
• /
• pp.23-36
• /
• 2003

학습에 대한 이해-기반 접근에 따르면 새로운 정보는 기존의 배경지식과 통합되어 정신표상을 형성하며 이는 다른 새로운 정보를 결합하는데 사용된다고 가정한다. 지시문을 통한 학습상황에서 인간과 계산적 모형의 수행비교를 통해 이 접근법이 타당하다는 것을 보여주었다. 구성-통합 이론 (Kintsch, 1988; 1998)에 근거한 계산적 모형 (ADAPT-UNIX)은 사용자들이 UNIX 복합 명령문을 생성하는데 도움을 주기위해 제시된 지시문 학습에 높은 예측력을 보였다. 더불어, 제시된 지시문을 사용하여 올바른 복합명령문을 생성하는 과제수행도 실제 인간수행과 높은 유사성 보였다. 배경지식의 수준에 따라 지시문이 학습과 적용에 차별적인 영향을 미친다는 교육적 함의와 이해-기반 인지모델의 이론적 함의가 논의되었다.

• 공학교육연구
• /
• 제20권1호
• /
• pp.53-62
• /
• 2017

This paper explored how university students viewed flipped learning from their own perspectives. Using qualitative research methods, 5 students from a Computer Graphics course at a mid-scale university in Seoul were interviewed for this purpose. Researchers collected data about their learning experiences, emotions, and reflections about flipped learning in general and its components such as online materials, in-class activities, and instructor guidance. Research findings indicated that students were not so much conscious about the unfamiliarity of the class, the increased work load, nor the online lectures. They rather prioritized 'what they could actually learn' from the course, and thus defined flipped learning as a method which enabled students to constantly check and fill in the gaps in their learning through team-based activities and prompt feedback from the professor. A combination of students' positive attitude and active participation in team-based activities, the overall atmosphere of the department which supported interactivity and collaboration, the professor's emphasis on learning-by-doing and student-centered learning appeared to form their notions of flipped learning. The use of technology did not appear to heavily impact students' conceptions of flipped learning. Researchers suggest that pedagogical beliefs of the professor, culture surrounding the learner, and the good match between the course content and instructional strategies are central for designing a successful flipped learning class.

• Nuclear Engineering and Technology
• /
• 제55권5호
• /
• pp.1708-1717
• /
• 2023

The grade analysis of lead-zinc ore is the basis for the optimal development and utilization of deposits. In this study, a method combining Prompt Gamma Neutron Activation Analysis (PGNAA) technology and machine learning is proposed for lead-zinc mine borehole logging, which can identify lead-zinc ores of different grades and gangue in the formation, providing real-time grade information qualitatively and semi-quantitatively. Firstly, Monte Carlo simulation is used to obtain a gamma-ray spectrum data set for training and testing machine learning classification algorithms. These spectra are broadened, normalized and separated into inelastic scattering and capture spectra, and then used to fit different classifier models. When the comprehensive grade boundary of high- and low-grade ores is set to 5%, the evaluation metrics calculated by the 5-fold cross-validation show that the SVM (Support Vector Machine), KNN (K-Nearest Neighbor), GNB (Gaussian Naive Bayes) and RF (Random Forest) models can effectively distinguish lead-zinc ore from gangue. At the same time, the GNB model has achieved the optimal accuracy of 91.45% when identifying high- and low-grade ores, and the F₁ score for both types of ores is greater than 0.9.

• 패션비즈니스
• /
• 제28권3호
• /
• pp.122-139
• /
• 2024

Image-generated AI is rapidly emerging as a powerful tool to augment human creativity and transform the art and design process through deep learning capabilities. The purpose of this study was to propose and demonstrate the feasibility of a new design development method that combined traditional design methods and technology by constructing image-generated AI prompts based on artists' formative elements. The study methodology consisted of analyzing Kazmir Malevich's theoretical considerations and applying them to AI prompts for design, print pattern development, and 3D digital design. This study found that the suprematist works of Kazmir Malevich were suitable as design and print pattern prompts due to their clear geometric shapes, colors, and spatial arrangement. The AI-prompted designs and print patterns produced diverse results quickly and enabled an efficient design process compared to traditional methods, although additional refinement was required to perfect the details. The AI-generated designs were successfully produced as 3D garments, thereby demonstrating that AI technology could significantly contribute to fashion design through its integration with artistic principles. This study has academic significance in that it proposes a prompt composition method applicable to fashion design by combining AI and artistic elements. It also has industrial significance in that it contributes to design innovation and the implementation of creative ideas by presenting an AI-based design process that can be practically applied.

• 스마트미디어저널
• /
• 제7권4호
• /
• pp.79-89
• /
• 2018

In recent years, falls among elderly people have gained serious attention as a major cause of injuries. Falls often lead to fatal consequences due to lack of prompt response and rescue. Therefore, a more accurate fall detection system and an effective feature extraction technique are required to prevent and reduce the risk of such incidents. In this paper, we proposed an efficient feature extraction technique based on multiple sliding windows and validated it through a series of experiments using supervised learning algorithms. The experiments were conducted using the public datasets obtained from tri-axial accelerometers. The results depicted that extraction of the feature from adjacent sliding windows led to high accuracy in supervised machine learning-based fall detection. Also, the experiments conducted in this study suggested that the best accuracy can be achieved by keeping the window size as small as 2 seconds. With the kNN classifier and dataset from wearable sensors, the experiments achieved accuracy rates of 94%.

• 한국정보과학회 언어공학연구회:학술대회논문집(한글 및 한국어 정보처리)
• /
• 한국정보과학회언어공학연구회 2022년도 제34회 한글 및 한국어 정보처리 학술대회
• /
• pp.343-347
• /
• 2022

최근 자연어처리 분야에서는 BERT, RoBERTa, 그리고 BART와 같은 사전 학습된 언어 모델 (Pre-trained Language Models, PLM) 기반 미세 조정 학습을 통하여 여러 하위 과업에서 좋은 성능을 거두고 있다. 이는 사전 학습된 언어 모델 및 데이터 집합의 크기, 그리고 모델 구성의 중요성을 보여주며 대규모 사전 학습된 언어 모델이 각광받는 계기가 되었다. 하지만, 거대한 모델의 크기로 인하여 실제 산업에서 쉽게 쓰이기 힘들다는 단점이 명백히 존재함에 따라 최근 매개변수 효율적인 미세 조정 및 Few-Shot 학습 연구가 많은 주목을 받고 있다. 본 논문은 Prompt tuning, Prefix tuning와 프롬프트 기반 미세 조정 (Prompt-based fine-tuning)을 결합한 Few-Shot 학습 연구를 제안한다. 제안한 방법은 미세 조정 ←→ 사전 학습 간의 지식 격차를 줄일 뿐만 아니라 기존의 일반적인 미세 조정 기반 Few-Shot 학습 성능보다 크게 향상됨을 보인다.

• Nuclear Engineering and Technology
• /
• 제55권2호
• /
• pp.493-505
• /
• 2023

Comprehensive condition monitoring of large industry systems such as nuclear power plants (NPPs) is essential for safety and maintenance. In this study, we developed novel system-scale diagnostic technology based on deep-learning and IR thermography that can efficiently and cost-effectively classify system conditions using compact Raspberry Pi and IR sensors. This diagnostic technology can identify the presence of an abnormality or accident in whole system, and when an accident occurs, the type of accident and the location of the abnormality can be identified in real-time. For technology development, the experiment for the thermal image measurement and performance validation of major components at each accident condition of NPPs was conducted using a thermal-hydraulic integral effect test facility with compact infrared sensor modules. These thermal images were used for training of deep-learning model, convolutional neural networks (CNN), which is effective for image processing. As a result, a proposed novel diagnostic was developed that can perform diagnosis of components, whole system and accident classification using thermal images. The optimal model was derived based on the modern CNN model and performed prompt and accurate condition monitoring of component and whole system diagnosis, and accident classification. This diagnostic technology is expected to be applied to comprehensive condition monitoring of nuclear power plants for safety.