DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | Hwang, Sung Ju | - |
dc.contributor.advisor | 황성주 | - |
dc.contributor.author | Willette, Jeffrey Ryan | - |
dc.date.accessioned | 2022-04-27T19:32:13Z | - |
dc.date.available | 2022-04-27T19:32:13Z | - |
dc.date.issued | 2021 | - |
dc.identifier.uri | http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=963378&flag=dissertation | en_US |
dc.identifier.uri | http://hdl.handle.net/10203/296161 | - |
dc.description | 학위논문(석사) - 한국과학기술원 : 전산학부, 2021.8,[iii, 21 p. :] | - |
dc.description.abstract | Neural networks have proven successful at learning from complex data distributions by acting as universal function approximators. However, they are often overconfident in their predictions, which leads to inaccurate and miscalibrated probabilistic predictions. The problem of overconfidence becomes especially apparent in cases where the test-time data distribution differs from that which was seen during training. We propose a solution to this problem by seeking out regions of feature space where the model is unjustifiably overconfident, and conditionally raising the entropy of those predictions towards that of the prior distribution of the labels. Our method results in a better calibrated network and is agnostic to the underlying model structure, so it can be applied to any neural network which produces a probability density as an output. We demonstrate the effectiveness of our method and validate its performance on both classification and regression problems, applying it to recent probabilistic neural network models. | - |
dc.language | eng | - |
dc.publisher | 한국과학기술원 | - |
dc.subject | Deep learning▼aBayesian inference▼aUncertainty calibration▼aNeural networks▼aSafe AI | - |
dc.subject | 딥러닝▼a베이지안 추론▼a불확실성 추론▼a인공신경망▼a안전한 인공지능 | - |
dc.title | Uncertainty calibration in deep learning | - |
dc.title.alternative | 딥러닝의 불확실성 보정에 관한 연구 | - |
dc.type | Thesis(Master) | - |
dc.identifier.CNRN | 325007 | - |
dc.description.department | 한국과학기술원 :전산학부, | - |
dc.contributor.alternativeauthor | 위레트제프리 | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.