Schedule

Session 1

• 8:45am - 9:00am Opening remarks
• 9:00am - 9:10am Contributed #1: Probabilistic Deep Learning using Random Sum-Product Networks
• 9:10am - 10:00am Spotlight presentations (2 mins per poster)
• 10:00am - 10:30am Poster Session

Coffee Break: 10:30-11:00am

Session 2

• 11:10am - 11:20am Contributed #2: Uncertainty in the Variational Information Bottleneck
• 11:20am - 11:50am Sergey Levine: Probabilistic Deep Reinforcement Learning: Robustness, Uncertainty, and Safety
• 11:50am - 12:00pm Contributed #3: Learn to Adapt Uncertainty with Stochastic Activation Actor-Critic Methods
• 12:00pm - 12:30pm Yingzhen Li: Meta learning for stochastic gradient MCMC

Lunch: 12:30-2:00pm

Session 3

• 2:00pm - 2:10pm Contributed #4: Fast Uncertainty Estimates and Bayesian Model Averaging of DNNs
• 2:10pm - 2:40pm Volodymyr Kuleshov: Calibrated Uncertainty in Deep Learning
• 2:40pm - 2:50pm Contributed #5: To Trust Or Not To Trust A Classifier
• 2:50pm - 3:20pm Rich Caruana: Friends Don’t Let Friends Deploy Black-Box Models: The Importance of Intelligibility in Machine Learning
• 3:20pm - 3:30pm Contributed #6: Countdown Regression: Sharp and Calibrated Survival Predictions

Coffee Break: 3:30-4:00pm

Session 4

• 4:00pm - 4:30pm Zoubin Ghahramani: Uncertainty, Probabilities, and Deep Learning
• 4:30pm - 5:15pm Panel discussion
• 5:15pm - 6pm Poster Session