1 Hit in 1.6 sec

BayesAdapter: Being Bayesian, Inexpensively and Reliably, via Bayesian Fine-tuning [article]

Zhijie Deng, Hao Zhang, Xiao Yang, Yinpeng Dong, Jun Zhu
2021 arXiv   pre-print
In particular, we propose to adapt the pre-trained deterministic NNs to be BNNs via cost-effective Bayesian fine-tuning.  ...  Despite their theoretical appealingness, Bayesian neural networks (BNNs) are left behind in real-world adoption, due to persistent concerns on their scalability, accessibility, and reliability.  ...  The shared parameters w can be initialized as w * to ease and speedup the Bayesian fine-tuning.  ... 
arXiv:2010.01979v4 fatcat:nhiu3neenjb7johs5hc5husyiq