Challenging common interpretability assumptions in feature attribution explanations
Dec 6, 2020
Speakers
Jonathan Dinu
Speaker · 0 followers
Jeffrey Bigham
Speaker · 0 followers
Zico Kolter
Speaker · 2 followers
Organizer
NeurIPS 2020
Account · 11.5k followers
Categories
Computer Science & IT
Category · 14.8k presentations
About NeurIPS 2020
Neural Information Processing Systems (NeurIPS) is a multi-track machine learning and computational neuroscience conference that includes invited talks, demonstrations, symposia and oral and poster presentations of refereed papers. Following the conference, there are workshops which provide a less formal setting.
Like the format? Trust SlidesLive to capture your next event!
Professional recording and live streaming, delivered globally.
Sharing
Recommended Videos
Presentations on similar topic, category or speaker
Average Reward Reinforcement Learning with Monotonic Policy Improvement
Watch later
Yiming Zhang, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Neural Methods for Point-wise Dependency Estimation
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Continuous Object Representation Networks: Novel View Synthesis without Target View Supervision
Watch later
Nicolai Hani, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Sheaf Neural Networks
Watch later
Jakob Hansen, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
Closing remarks
Watch later
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%
What Did You Think Would Happen? Explaining Agent Behaviour through Intended Outcomes
Watch later
Herman Yau, …
Total of 0 viewers voted for saving the presentation to eternal vault which is 0.0%