Timezone: »

 
Oral
Decomposition of Uncertainty in Bayesian Deep Learning for Efficient and Risk-sensitive Learning
Stefan Depeweg · Jose Miguel Hernandez-Lobato · Finale Doshi-Velez · Steffen Udluft

Thu Jul 12 07:30 AM -- 07:40 AM (PDT) @ A4
in Deep Learning (Bayesian) 2 »

Bayesian neural networks with latent variables arescalable and flexible probabilistic models: theyaccount for uncertainty in the estimation of thenetwork weights and, by making use of latent variables,can capture complex noise patterns in thedata. Using these models we show how to performand utilize a decomposition of uncertainty inaleatoric and epistemic components for decisionmaking purposes. This allows us to successfullyidentify informative points for active learning offunctions with heteroscedastic and bimodal noise.Using the decomposition we further define a novelrisk-sensitive criterion for reinforcement learningto identify policies that balance expected cost,model-bias and noise aversion.

[ PDF]  [ Video] 

Author Information

Stefan Depeweg (TU Munich)
Jose Miguel Hernandez-Lobato (University of Cambridge)
Finale Doshi-Velez (Harvard University)
Finale Doshi-Velez

Finale Doshi-Velez is a Gordon McKay Professor in Computer Science at the Harvard Paulson School of Engineering and Applied Sciences. She completed her MSc from the University of Cambridge as a Marshall Scholar, her PhD from MIT, and her postdoc at Harvard Medical School. Her interests lie at the intersection of machine learning, healthcare, and interpretability. Selected Additional Shinies: BECA recipient, AFOSR YIP and NSF CAREER recipient; Sloan Fellow; IEEE AI Top 10 to Watch

Steffen Udluft (Siemens AG)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors