http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
이동준(Dong-Joon Lee),박혜린(Hyeryn Park),이창희(Changhee Lee) 대한전자공학회 2023 대한전자공학회 학술대회 Vol.2023 No.6
The application of deep learning techniques in survival analysis has become increasingly significant as a means of comprehending the timing and incidence of specific events in various fields, such as medicine, engineering, and social sciences. However, due to the black-box nature of deep learning models, it is inherently difficult to understand the relationships between the variables and the time-to-event predictions provided by these models. In this paper, we propose a feature selection technique for deep survival network that can efficiently consider event-time information to select only appropriate variables to help train the model.