DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | Suh, Changho | - |
dc.contributor.advisor | 서창호 | - |
dc.contributor.author | Kim, Hoon | - |
dc.date.accessioned | 2019-09-04T02:42:15Z | - |
dc.date.available | 2019-09-04T02:42:15Z | - |
dc.date.issued | 2019 | - |
dc.identifier.uri | http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=843385&flag=dissertation | en_US |
dc.identifier.uri | http://hdl.handle.net/10203/266813 | - |
dc.description | 학위논문(석사) - 한국과학기술원 : 전기및전자공학부, 2019.2,[v, 38 p. :] | - |
dc.description.abstract | Deep learning has made great strides for problems that can be learned with direct supervision, in which a large dataset with high-quality annotation is provided (e.g., ImageNet). However, collecting such a large dataset is expensive and time-consuming. The goal of this work is to address this issue by utilizing computer simulation to train a machine learning model. First, we present our novel \emph{Simulated+Unsupervised (S+U) learning} algorithm, which fully leverages the flexibility of data simulators and bidirectional mappings between synthetic and real data. We show that our approach achieves the improved performance on the gaze estimation task, outperforming the prior approach by \cite{shrivastava2016learning}. Next, we introduce our work on building data-driven vehicle collision prediction algorithms. Today’s vehicle collision prediction algorithms are rule-based and have not benefited from the recent developments in deep learning. This is because it is almost impossible to collect a large amount of collision data from the real world. To address this challenge, we collect a large accident dataset using a popular video game named GTA and train end-to-end classification algorithms which identify dangerous objects from a given image. Furthermore, we devise a novel domain adaptation method with which we can further improve the performance of our algorithm in the real-world. | - |
dc.language | eng | - |
dc.publisher | 한국과학기술원 | - |
dc.subject | Deep learning▼asimulation▼agenerative adversarial network▼adomain adaptation▼asytle transfer▼acollision prediction▼aself driving | - |
dc.subject | 딥러닝▼a시뮬레이션▼a도메인 적응 기법▼a스타일 변환▼a층돌 예측 시스템▼a자율주행 | - |
dc.title | Learning from computer simulations to tackle real-world problems | - |
dc.title.alternative | 현실 세상의 문제 해결을 위한 시뮬레이터 기반 기계학습 | - |
dc.type | Thesis(Master) | - |
dc.identifier.CNRN | 325007 | - |
dc.description.department | 한국과학기술원 :전기및전자공학부, | - |
dc.contributor.alternativeauthor | 김훈 | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.