Filters








2 Hits in 3.5 sec

IDK Cascades: Fast Deep Learning by Learning not to Overthink [article]

Xin Wang, Yujia Luo, Daniel Crankshaw, Alexey Tumanov, Fisher Yu, Joseph E. Gonzalez
2018 arXiv   pre-print
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

A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challenges [article]

Moloud Abdar, Farhad Pourpanah, Sadiq Hussain, Dana Rezazadegan, Li Liu, Mohammad Ghavamzadeh, Paul Fieguth, Xiaochun Cao, Abbas Khosravi, U Rajendra Acharya, Vladimir Makarenkov, Saeid Nahavandi
2021 arXiv   pre-print
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.  ...  [252] 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