DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | 김주영 | - |
dc.contributor.author | Lim, Sukbin | - |
dc.contributor.author | 임석빈 | - |
dc.date.accessioned | 2024-07-25T19:31:20Z | - |
dc.date.available | 2024-07-25T19:31:20Z | - |
dc.date.issued | 2023 | - |
dc.identifier.uri | http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=1045935&flag=dissertation | en_US |
dc.identifier.uri | http://hdl.handle.net/10203/320704 | - |
dc.description | 학위논문(석사) - 한국과학기술원 : 전기및전자공학부, 2023.8,[iii, 20 p. :] | - |
dc.description.abstract | This paper proposes a large-scale point cloud deep neural network accelerator. It presents a novel concept of virtual pillars and proposes a skipping method based on the region of interest. Additionally, it maximizes slice-level sparsity by adopting the sign-magnitude representation method instead of the conventional two's complement representation. This work achieves a speedup of 5.3 times on feature encoding and shows 35.4 TOPS/W power efficiency on backbone. | - |
dc.language | eng | - |
dc.publisher | 한국과학기술원 | - |
dc.subject | 머신 러닝▼a딥-러닝▼a인공지능 하드웨어 가속기▼a점구름 데이터▼a자율 주행 | - |
dc.subject | Machine learning▼aDeep learning▼aArtificial intelligence accelerator▼aPoint cloud▼aAutonomous driving | - |
dc.title | (An) large-scale point cloud deep neural network accelerator with virtual pillar and ROI-based skipping | - |
dc.title.alternative | 가상 필러와 관심 영역 기반 스킵핑을 활용한 대규모 점구름 신경망 모델 인공지능 가속기 | - |
dc.type | Thesis(Master) | - |
dc.identifier.CNRN | 325007 | - |
dc.description.department | 한국과학기술원 :전기및전자공학부, | - |
dc.contributor.alternativeauthor | Kim, Joo-Young | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.