• 제목/요약/키워드: generative learning

검색결과 279건 처리시간 0.024초

Generative Adversarial Networks: A Literature Review

  • Cheng, Jieren;Yang, Yue;Tang, Xiangyan;Xiong, Naixue;Zhang, Yuan;Lei, Feifei
    • KSII Transactions on Internet and Information Systems (TIIS)
    • /
    • 제14권12호
    • /
    • pp.4625-4647
    • /
    • 2020
  • The Generative Adversarial Networks, as one of the most creative deep learning models in recent years, has achieved great success in computer vision and natural language processing. It uses the game theory to generate the best sample in generator and discriminator. Recently, many deep learning models have been applied to the security field. Along with the idea of "generative" and "adversarial", researchers are trying to apply Generative Adversarial Networks to the security field. This paper presents the development of Generative Adversarial Networks. We review traditional generation models and typical Generative Adversarial Networks models, analyze the application of their models in natural language processing and computer vision. To emphasize that Generative Adversarial Networks models are feasible to be used in security, we separately review the contributions that their defenses in information security, cyber security and artificial intelligence security. Finally, drawing on the reviewed literature, we provide a broader outlook of this research direction.

딥러닝 기반 교량 손상추정을 위한 Generative Adversarial Network를 이용한 가속도 데이터 생성 모델 (Generative Model of Acceleration Data for Deep Learning-based Damage Detection for Bridges Using Generative Adversarial Network)

  • 이강혁;신도형
    • 한국BIM학회 논문집
    • /
    • 제9권1호
    • /
    • pp.42-51
    • /
    • 2019
  • Maintenance of aging structures has attracted societal attention. Maintenance of the aging structure can be efficiently performed with a digital twin. In order to maintain the structure based on the digital twin, it is required to accurately detect the damage of the structure. Meanwhile, deep learning-based damage detection approaches have shown good performance for detecting damage of structures. However, in order to develop such deep learning-based damage detection approaches, it is necessary to use a large number of data before and after damage, but there is a problem that the amount of data before and after the damage is unbalanced in reality. In order to solve this problem, this study proposed a method based on Generative adversarial network, one of Generative Model, for generating acceleration data usually used for damage detection approaches. As results, it is confirmed that the acceleration data generated by the GAN has a very similar pattern to the acceleration generated by the simulation with structural analysis software. These results show that not only the pattern of the macroscopic data but also the frequency domain of the acceleration data can be reproduced. Therefore, these findings show that the GAN model can analyze complex acceleration data on its own, and it is thought that this data can help training of the deep learning-based damage detection approaches.

The Effects of Generative Concept Map on Science Learning Achievement and Cognitive Load

  • OH, Suna;KIM, Yeonsoon
    • Educational Technology International
    • /
    • 제17권2호
    • /
    • pp.253-271
    • /
    • 2016
  • This study investigated the effect of generative concept maps according to learning achievements and cognitive load. A total of 78 students in the first grade of middle school participated in this study. Before the experimental treatment was implemented, students had to fill out a questionnaire assessing prior knowledge. The study was designed where all the students were presented the same learning contents regarding photosynthesis; however, the two experimental groups were provided with different concept map methods: a learner-generative concept map (GCM) and an instructor-provided concept map (PCM). GCM students were asked to make a concept map by themselves in small groups while they are reading material. PCM students were instructed to study in small groups in order to read the material; however, they were provided a concept map developed by their teacher. The control group (CG) had the teacher present the learning contents in traditional lecture format with no accompanying concept map. The results show that there were significant differences in the achievements among the groups. CG showed higher achievement than both the experimental groups. There was also a significant difference in cognitive load. Although the GCM group did not obtain higher achievement than the other groups, the GCM group showed higher mental effort and lower physical fatigue than the other groups. The GCM group might have invested more effort to find and connect ideas when drawing their concept map with peers which is unlike the conditions for the PCM group and CG. In conclusion, we should consider applying GCM in teaching and learning design in order to increase learning achievement and decrease extraneous cognitive load.

참여형 학습에서 생성형 AI 지속 사용 의도에 대한 실증적 연구: ChatGPT 사례 중심으로 (An Empirical Study on the Intention to Continue Using Generative AI in Engaged Learning: Focusing on the ChatGPT Case)

  • 김경순;김낙일;김명수;신용태
    • 한국IT서비스학회지
    • /
    • 제22권6호
    • /
    • pp.17-35
    • /
    • 2023
  • This study investigated how helpful the use of generative AI such as ChatGPT is in conducting engaged learning at each university. In this study, based on the experiences of users using generative AI technology, we analyzed the relationship between usability and ease in consideration of the characteristics of learners, and examined whether there is an intention to continue using generative AI technology in the future. In this study, in order to verify the factors affecting the intention to use ChatGPT technology in order to solve the problems given in the participating classes, we examined previous papers based on the Technology Acceptance Model (TAM) and the Information System Success Model (IS), extracted the factors affecting the intention of ChatGPT technology, and presented the research model and hypothesis. Empirical research on the continuous use of generative AI in participatory learning using ChatGPT was conducted to determine whether it is suitable for long-term and continuous use in the educational environment, and whether it is sustainable by examining the intention of learners to continue using it. First, user satisfaction was positively related to the intention to continue using generative AI technology. Second, if the user experience has a great influence on the intention to continue using ChatGPT technology, and users gain experiences such as usefulness, interest, and effective response in the process of using the technology, the evaluation of the technology is positively formed and the intention to continue using it is high. Third, the ease of use of the technology also showed that it was intended to be used continuously when an environment was provided in which users could easily and conveniently utilize generative AI technology.

생성적 적대 신경망(GAN)을 이용한 한국어 문서에서의 문맥의존 철자오류 교정 (Context-Sensitive Spelling Error Correction Techniques in Korean Documents using Generative Adversarial Network)

  • 이정훈;권혁철
    • 한국멀티미디어학회논문지
    • /
    • 제24권10호
    • /
    • pp.1391-1402
    • /
    • 2021
  • This paper focuses use context-sensitive spelling error correction using generative adversarial network. Generative adversarial network[1] are attracting attention as they solve data generation problems that have been a challenge in the field of deep learning. In this paper, sentences are generated using word embedding information and reflected in word distribution representation. We experiment with DCGAN[2] used for the stability of learning in the existing image processing and D2GAN[3] with double discriminator. In this paper, we experimented with how the composition of generative adversarial networks and the change of learning corpus influence the context-sensitive spelling error correction In the experiment, we correction the generated word embedding information and compare the performance with the actual word embedding information.

Generative AI parameter tuning for online self-directed learning

  • Jin-Young Jun;Youn-A Min
    • 한국컴퓨터정보학회논문지
    • /
    • 제29권4호
    • /
    • pp.31-38
    • /
    • 2024
  • 본 연구는 온라인 원격교육에서 코딩 교육 활성화를 위해, 생성형 AI 기반의 학습 지원 도구개발에 필요한 하이퍼 파라미터 설정을 제안한다. 연구를 위해 세 가지 다른 학습 맥락에 따라 하이퍼 파라미터를 설정할 수 있는 실험 도구를 구현하고, 실험 도구를 통해 생성형 AI의 응답 품질을 평가하였다. 생성형 AI 자체의 기본 하이퍼 파라미터 설정을 유지한 실험은 대조군으로, 연구에서 설정한 하이퍼 파라미터를 사용한 실험은 실험군으로 하였다. 실험 결과, 첫 번째 학습맥락인 "학습 지원"에서는 실험군과 대조군 사이의 유의한 차이가 관찰되지 않았으나, 두 번째와 세 번째 학습 맥락인 "코드생성"과 "주석생성"에서는 실험군의 평가점수 평균이 대조군보다 각각 11.6% 포인트, 23% 포인트 높은 것으로 나타났다. 또한, system content에 응답이 학습 동기에 미칠 수 있는 영향을 제시하면 학습 정서를 고려한 응답이 생성되는 것이 관찰되었다.

Generative Adversarial Network를 이용한 손실된 깊이 영상 복원 (Depth Image Restoration Using Generative Adversarial Network)

  • 나준엽;심창훈;박인규
    • 방송공학회논문지
    • /
    • 제23권5호
    • /
    • pp.614-621
    • /
    • 2018
  • 본 논문에서는 generative adversarial network (GAN)을 이용한 비감독 학습을 통해 깊이 카메라로 깊이 영상을 취득할 때 발생한 손실된 부분을 복원하는 기법을 제안한다. 제안하는 기법은 3D morphable model convolutional neural network (3DMM CNN)와 large-scale CelebFaces Attribute (CelebA) 데이터 셋 그리고 FaceWarehouse 데이터 셋을 이용하여 학습용 얼굴 깊이 영상을 생성하고 deep convolutional GAN (DCGAN)의 생성자(generator)와 Wasserstein distance를 손실함수로 적용한 구별자(discriminator)를 미니맥스 게임기법을 통해 학습시킨다. 이후 학습된 생성자와 손실 부분을 복원해주기 위한 새로운 손실함수를 이용하여 또 다른 학습을 통해 최종적으로 깊이 카메라로 취득된 얼굴 깊이 영상의 손실 부분을 복원한다.

국방용 합성이미지 데이터셋 생성을 위한 대립훈련신경망 기술 적용 연구 (Synthetic Image Dataset Generation for Defense using Generative Adversarial Networks)

  • 양훈민
    • 한국군사과학기술학회지
    • /
    • 제22권1호
    • /
    • pp.49-59
    • /
    • 2019
  • Generative adversarial networks(GANs) have received great attention in the machine learning field for their capacity to model high-dimensional and complex data distribution implicitly and generate new data samples from the model distribution. This paper investigates the model training methodology, architecture, and various applications of generative adversarial networks. Experimental evaluation is also conducted for generating synthetic image dataset for defense using two types of GANs. The first one is for military image generation utilizing the deep convolutional generative adversarial networks(DCGAN). The other is for visible-to-infrared image translation utilizing the cycle-consistent generative adversarial networks(CycleGAN). Each model can yield a great diversity of high-fidelity synthetic images compared to training ones. This result opens up the possibility of using inexpensive synthetic images for training neural networks while avoiding the enormous expense of collecting large amounts of hand-annotated real dataset.

생성형 인공지능을 활용한 사례 기반 간호 교육 프로그램 개발 (Development of a case-based nursing education program using generative artificial intelligence)

  • 안정희;박혜옥
    • 한국간호교육학회지
    • /
    • 제29권3호
    • /
    • pp.234-246
    • /
    • 2023
  • Purpose: This study aimed to develop a case-based nursing education program using generative artificial intelligence and to assess its usability and applicability in nursing curriculums. Methods: The program was developed by following the five steps of the ADDIE model: analysis, design, development, implementation, and evaluation. A panel of five nursing professors served as experts to implement and evaluate the program. Results: Utilizing ChatGPT, six program modules were designed and developed based on experiential learning theory. The experts' evaluations confirmed that the program was suitable for case-based learning, highly usable, and applicable to nursing education. Conclusion: Generative artificial intelligence was identified as a valuable tool for enhancing the effectiveness of case-based learning. This study provides insights and future directions for integrating generative artificial intelligence into nursing education. Further research should be attempted to implement and evaluate this program with nursing students.

생성모형의 학습을 위한 상향전파알고리듬 (Learning Generative Models with the Up-Propagation Algorithm)

  • 오종훈
    • 한국정보과학회:학술대회논문집
    • /
    • 한국정보과학회 1998년도 가을 학술발표논문집 Vol.25 No.2 (2)
    • /
    • pp.327-329
    • /
    • 1998
  • Up-Propagation is an algorithm for inverting and learning neural network generative models. Sensory input is processed by inverting a model that generates patterns from hidden variables using top-down connections. The inversion process is iterative, utilizing a negative feedback loop that depends on an error signal propagated by bottom-up connections. The error signal is also used to learn the generative model from examples. the algorithm is benchmarked against principal component analysis in experiments on images of handwritten digits.

  • PDF