A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is
Advances in deep learning have led to substantial increases in prediction accuracy but have been accompanied by increases in the cost of rendering predictions. ... We conjecture that fora majority of real-world inputs, the recent advances in deep learning have created models that effectively "overthink" on simple inputs. ... Acknowledgements This research is supported in part by DHS Award HSHQDC-16-3-00083, NSF CISE Expeditions Award CCF-1139158, and gifts from Alibaba, Amazon Web Services, Ant Financial, CapitalOne, Ericsson ...arXiv:1706.00885v4 fatcat:d34s54tttred7ps4wtwhctgsx4
This study reviews recent advances in UQ methods used in deep learning. Moreover, we also investigate the application of these methods in reinforcement learning (RL). ... It can be applied to solve a variety of real-world applications in science and engineering. ...  speculated that for many of the real world inputs, deep learning models created recently, it tended to "overthink" on simple inputs. ...arXiv:2011.06225v4 fatcat:wwnl7duqwbcqbavat225jkns5u