• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.05a
• /
• pp.356-358
• /
• 2022

추천 시스템에서 사용되는 피드백은 단일 클래스와 다중 클래스 피드백으로 구분할 수 있다. 추천 시스템을 위한 지식 증류 기법들은 단일 클래스 환경에서 주로 연구되어 왔다. 우리는 다중 클래스 환경에서 또한 추천 시스템을 위한 최신 지식 증류 기법들이 효과적인지에 대해 알아보고자 하며, 해당 방법들 간의 추천 정확도를 비교해보고자 한다. 추천 시스템에서 보편적으로 사용되는 데이터 셋들을 기반으로 한 실험들을 통해 추천 시스템을 위한 지식 증류 기법들은 같은 조건의 기본적인 추천 시스템에 비해 정확도가 최대 193%까지 개선되는 것을 확인했다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.05a
• /
• pp.530-531
• /
• 2023

딥러닝에서 지식 증류 기법은 큰 모델의 지식을 작은 모델로 전달하여 작은 모델의 성능을 개선하는 방식이다. 지식 증류 기법은 모델 경량화, 학습 속도 향상, 학습 정확도 향상 등에 활용될 수 있는데, 교사 모델이라 불리는 큰 모델은 일반적으로 학습된 딥러닝 모델을 사용한다. 본 연구에서는 학습된 딥러닝 모델 대신에 수치 기반 시뮬레이션 모델을 사용함으로써 어떠한 효과가 있는지 검증하였으며, 수치 모델을 활용한 기상 예측 모델에서의 지식 증류는 기존 단독 딥러닝 모델 학습 대비 더 작은 학습 횟수(epoch)에서도 동일한 에러 수준(RMSE)까지 도달하여, 학습 속도 측면에서 이득이 있음을 확인하였다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.524-525
• /
• 2023

설명 가능한 심층 강화 학습 지식 증류 방법(ERL-KD)이 제안하였다. 이 방법은 모든 하위 에이전트로부터 점수를 수집하며, 메인 에이전트는 주 교사 네트워크 역할을 하고 하위 에이전트는 보조 교사 네트워크 역할을 한다. 글로벌 최적 솔루션은 샤플리 값과 같은 해석 가능한 방법을 통해 얻어진다. 또한 유사도 제약이라는 개념을 도입하여 교사 네트워크와 학생 네트워크 간의 유사도를 조정함으로써 학생 네트워크가 자유롭게 탐색할 수 있도록 유도한다. 실험 결과, 학생 네트워크는 아타리 2600 환경에서 대규모 교사 네트워크와 비슷한 성능을 달성하는 것으로 나타났다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.695-697
• /
• 2023

최근 몇 년 간 딥러닝 기반 모델의 규모와 복잡성이 증가하면서 강력하고, 높은 정확도가 확보되지만 많은 양의 계산 자원과 메모리가 필요하기 때문에 모바일 장치나 임베디드 시스템과 같은 리소스가 제한된 환경에서의 배포에 제약사항이 생긴다. 복잡한 딥러닝 모델의 배포 및 운영 시 요구되는 고성능 컴퓨터 자원의 문제점을 해결하고자 사전 학습된 대규모 모델로부터 가벼운 모델을 학습시키는 지식증류 기법이 제안되었다. 하지만 현대 딥러닝 기반 모델은 높은 정확도 대비 훈련 데이터에 과적합 되는 과잉 확신(overconfidence) 문제에 대한 대책이 필요하다. 본 논문은 효율적인 경량화를 위한 미리 학습된 모델의 과잉 확신을 방지하고자 초점 손실(focal loss)을 이용한 모델 보정 기법을 언급하며, 다양한 손실 함수 변형에 따라서 지식증류의 성능이 어떻게 변화하는지에 대해 탐구하고자 한다.

• Korean Chemical Engineering Research
• /
• v.43 no.4
• /
• pp.458-466
• /
• 2005

Full-scale utilizations of batch separation process often require knowledge about thermodynamics and correlation techniques of physical properties of complex mixture consisting of a great number of many unknown components. Various empirical correlations have been proposed to predict the physical properties mostly about the pseudocomponent of petroleum. In this study, one parameter correlations are developed for the calculations of the critical physical properties and ideal heat capacity of the pseudo-component of coal tar fractions. Developed model can provide a tool for the design and operations for the batch distillation of coal tar mixture.

• Journal of Community Nutrition
• /
• v.2 no.1
• /
• pp.52-61
• /
• 2000

Dietary guidelines are a distillation of dietary advice from health professionals to the general public. They are based upon current scientific knowledge about the relationships between diet and disease, nutrients available in the food supply of a country, and the profile of morbidity and mortality in that country. With two different sets of dietary guidelines used for more than an decade in Korea. the necessity of revising dietary guidelines has been raised continuously from academia and research. Funded by a grant from the Health Technology Planing and Evaluation Board. Dietary guidelines for each age group were drafted as a research project and the one for the Korean elderly is as follows: Dietary Guidelines for the korean elderly(draft) - Have a variety of easily digestible foods on time; at least 3 meals a day and some snakes. - Be physically active to maintain appetite and/or ideal body weight. ; maintain a balance between activity and what you eat. -Increase consumption of bean-and dairy-and dairy-products. - Consume enough amounts of fresh dark-green and yellow vegetables and fresh fruits. - Consume adequate amounts of assorted kind of animal foods including fish, meat and poultry. - If you drink alcoholic beverages, limit your intake and, drink enough water and other averages; alcohol may interact with your medication and affect your appetite. Aforementioned draft and related contents are expected to be utilized as a neat base in formulating(or revising) dietary guidelines for Korean by the Government in near future.

• Journal of Intelligence and Information Systems
• /
• v.28 no.3
• /
• pp.45-55
• /
• 2022

Recently, large-scale language models (LPLM) have been shown state-of-the-art performances in various tasks of natural language processing including intent classification. However, fine-tuning LPLM requires much computational cost for training and inference which is not appropriate for dialog system. In this paper, we propose compressed intent classification model for multi-agent in low-resource like CPU. Our method consists of two stages. First, we trained sentence encoder from LPLM then compressed it through knowledge distillation. Second, we trained agent-specific adapter for intent classification. The results of three intent classification datasets show that our method achieved 98% of the accuracy of LPLM with only 21% size of it.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.46 no.1
• /
• pp.55-67
• /
• 2023

Lightweight face recognition models, as one of the most popular and long-standing topics in the field of computer vision, has achieved vigorous development and has been widely used in many real-world applications due to fewer number of parameters, lower floating-point operations, and smaller model size. However, few surveys reviewed lightweight models and reimplemented these lightweight models by using the same calculating resource and training dataset. In this survey article, we present a comprehensive review about the recent research advances on the end-to-end efficient lightweight face recognition models and reimplement several of the most popular models. To start with, we introduce the overview of face recognition with lightweight models. Then, based on the construction of models, we categorize the lightweight models into: (1) artificially designing lightweight FR models, (2) pruned models to face recognition, (3) efficient automatic neural network architecture design based on neural architecture searching, (4) Knowledge distillation and (5) low-rank decomposition. As an example, we also introduce the SqueezeFaceNet and EfficientFaceNet by pruning SqueezeNet and EfficientNet. Additionally, we reimplement and present a detailed performance comparison of different lightweight models on the nine different test benchmarks. At last, the challenges and future works are provided. There are three main contributions in our survey: firstly, the categorized lightweight models can be conveniently identified so that we can explore new lightweight models for face recognition; secondly, the comprehensive performance comparisons are carried out so that ones can choose models when a state-of-the-art end-to-end face recognition system is deployed on mobile devices; thirdly, the challenges and future trends are stated to inspire our future works.

• Journal of Physiology & Pathology in Korean Medicine
• /
• v.38 no.2
• /
• pp.49-58
• /
• 2024

The rapid advancement of generative large language models has revolutionized various real-life domains, emphasizing the importance of exploring their applications in healthcare. This study aims to examine how generative large language models are implemented in the medical domain, with the specific objective of searching for the possibility and potential of integration between generative large language models and East Asian medicine. Through a comprehensive current state analysis, we identified limitations in the deployment of generative large language models within East Asian medicine and proposed directions for future research. Our findings highlight the essential need for accumulating and generating structured data to improve the capabilities of generative large language models in East Asian medicine. Additionally, we tackle the issue of hallucination and the necessity for a robust model evaluation framework. Despite these challenges, the application of generative large language models in East Asian medicine has demonstrated promising results. Techniques such as model augmentation, multimodal structures, and knowledge distillation have the potential to significantly enhance accuracy, efficiency, and accessibility. In conclusion, we expect generative large language models to play a pivotal role in facilitating precise diagnostics, personalized treatment in clinical fields, and fostering innovation in education and research within East Asian medicine.