DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | 최성희 | - |
dc.contributor.author | Hyun, Ji-Hoon | - |
dc.contributor.author | 현지훈 | - |
dc.date.accessioned | 2024-08-08T19:30:17Z | - |
dc.date.available | 2024-08-08T19:30:17Z | - |
dc.date.issued | 2024 | - |
dc.identifier.uri | http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=1097314&flag=dissertation | en_US |
dc.identifier.uri | http://hdl.handle.net/10203/321789 | - |
dc.description | 학위논문(석사) - 한국과학기술원 : 전산학부, 2024.2,[iii, 15 p. :] | - |
dc.description.abstract | Recent studies and applications in machine learning shows that neural network using gradient descent-based methods suits the need in many cases. Especially, there have been many researches which talks about the importance of choosing a loss function, when using such methods. While there also have been studies which accepted the concept of meta-learning and substituted the loss function with a computational graph or a neural network, they didn’t question about the necessity of the loss function if they were to be replaced. This paper first looks the structural properties of neural networks. Also, the paper rethinks the role of loss function in neural networks, then gives an idea and method of learning the derivative of the loss function, and finally shows some experimental results on regression. | - |
dc.language | eng | - |
dc.publisher | 한국과학기술원 | - |
dc.subject | 메타 학습▼a최적화▼a경사하강법▼a딥러닝▼a인공 신경망 | - |
dc.subject | Meta learning▼aOptimization▼aGradient descent▼aDeep learning▼aNeural network | - |
dc.title | Training neural network through learning the derivative of loss function | - |
dc.title.alternative | 손실 함수의 도함수의 학습을 통한 인공신경망 학습 | - |
dc.type | Thesis(Master) | - |
dc.identifier.CNRN | 325007 | - |
dc.description.department | 한국과학기술원 :전산학부, | - |
dc.contributor.alternativeauthor | Choi, Sunghee | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.