http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Two-Dimensional Attention-Based LSTM Model for Stock Index Prediction
Yeonguk Yu,김윤중 한국정보처리학회 2019 Journal of information processing systems Vol.15 No.5
This paper presents a two-dimensional attention-based long short-memory (2D-ALSTM) model for stockindex prediction, incorporating input attention and temporal attention mechanisms for weighting of importantstocks and important time steps, respectively. The proposed model is designed to overcome the long-termdependency, stock selection, and stock volatility delay problems that negatively affect existing models. The 2DALSTMmodel is validated in a comparative experiment involving the two attention-based models multi-inputLSTM (MI-LSTM) and dual-stage attention-based recurrent neural network (DARNN), with real stock databeing used for training and evaluation. The model achieves superior performance compared to MI-LSTM andDARNN for stock index prediction on a KOSPI100 dataset.
Two-Dimensional Attention-Based LSTM Model for Stock Index Prediction
Yu, Yeonguk,Kim, Yoon-Joong Korea Information Processing Society 2019 Journal of information processing systems Vol.15 No.5
This paper presents a two-dimensional attention-based long short-memory (2D-ALSTM) model for stock index prediction, incorporating input attention and temporal attention mechanisms for weighting of important stocks and important time steps, respectively. The proposed model is designed to overcome the long-term dependency, stock selection, and stock volatility delay problems that negatively affect existing models. The 2D-ALSTM model is validated in a comparative experiment involving the two attention-based models multi-input LSTM (MI-LSTM) and dual-stage attention-based recurrent neural network (DARNN), with real stock data being used for training and evaluation. The model achieves superior performance compared to MI-LSTM and DARNN for stock index prediction on a KOSPI100 dataset.
유연국 ( Yeonguk Yu ),천용상 ( Yongsang Cheon ),조민희 ( Min-hee Cho ),김윤중 ( Yoon-joong Kim ) 한국정보처리학회 2019 한국정보처리학회 학술대회논문집 Vol.26 No.2
주가 예측은 상업적인 매력 때문에 많은 이목이 끌리는 분야이지만, 주가의 불확실성과 변동성 때문에 주가 예측은 어려운 작업이다. 최근에는 주가 예측 모델에 어텐션 메커니즘을 사용하여 주가 예측에 많은 인자들이 사용되어 생기는 성능 하락 문제를 해결하여 좋은 성능을 보여주는 연구가 존재한다. 본 연구에서는 그 모델 중 하나인 Dual-Stage Attention-Based Recurrent Neural Network (DARNN)의 어텐션 메커니즘을 변경해가며 어떤 어텐션 메커니즘이 주가 예측에 적합한지를 알아본다. KOSPI100 지수의 예측실험을 통해 location 스코어함수를 사용한 어텐션 메커니즘이 가장 뛰어난 성능을 보여주는 것을 확인하였고, 이는 기존의 스코어함수를 사용한 DARNN에 비해 약 10% 향상된 성능으로 스코어 함수가 모델의 중요한 영향을 끼치는 것을 확인하였다.
Learning to Box: Reinforcement Learning using Heuristic Three-step Curriculum Learning
Heeseon Rho,Yeonguk Yu,Kyoobin Lee 제어로봇시스템학회 2022 제어로봇시스템학회 국제학술대회 논문집 Vol.2022 No.11
The reinforcement learning paradigm is a widely used approach to solving sequential problems. In this paper, we utilized reinforcement learning with curriculum learning to train the agent to play boxing without any human demonstration. We presented as a curriculum three steps for a single agent to learn boxing: standing, walking and punching. The agent who learned through the proposed curriculum successfully threw a jab into a punching bag, but the agent who trained to punch from the beginning did not. Not only did we show the effectiveness of curriculum learning in single-agent boxing, but we also showed that the agent could play boxing without human demonstrations.