Decomposition of Uncertainty in Bayesian Deep Learning for Efficient and Risk-sensitive Learning.
Stefan DepewegJosé Miguel Hernández-LobatoFinale Doshi-VelezSteffen UdluftPublished in: ICML (2018)
Keyphrases
- deep learning
- learning algorithm
- learning process
- machine learning
- reinforcement learning
- risk sensitive
- deep architectures
- online learning
- supervised learning
- unsupervised learning
- learning tasks
- dynamic programming
- bayesian networks
- markov decision processes
- belief functions
- decision theory
- weakly supervised
- data mining