Schedule
MORNING SESSION
08:50 AM -- Introduction and opening remarks. Alessandra Tosi, Alfredo Vellido and Mauricio Alvarez
09:10 AM -- Invited talk: Is interpretability and explainability enough for safe and reliable decision making? SUCHI SARIA
09:45 AM -- Invited talk: The Role of Explanation in Holding AIs Accountable. FINALE DOSHI-VELEZ
10:20 AM -- Contributed talk: Beyond Sparsity: Tree-based Regularization of Deep Models for Interpretability. Wu, Hughes, Parbhoo, Doshi-Velez
10:30 AM -- Coffee break
11:00 AM -- Invited talk: Challenges for transparency. ADRIAN WELLER
11:20 AM -- Contributed talk: Safe Policy Search with Gaussian Process Models. Polymenakos, Roberts
11:30 AM -- Poster spotlights:
- Network Analysis for Explanation. Kuwajima, Tanaka
- Using prototypes to improve convolutional networks interpretability. Drumond, Vieville, Alexandre
- Accelerated Primal-Dual Policy Optimization for Safe Reinforcement Learning. Liang, Que, Modiano
- Deep Reinforcement Learning for Sepsis Treatment. Raghu, Komorowski, Szolovits, Ghassemi, Celi, Ahmed
- Analyzing Feature Relevance for Linear Reject Option SVM using Relevance Intervals. Göpfert
- The Neural LASSO: Local Linear Sparsity for Interpretable Explanations. Ross, Lage, Doshi-Velez
- Detecting Bias in Black-Box Models Using Transparent Model Distillation. Tan, Caruana, Hooker, Lou
- Data masking for privacy-sensitive learning. Pham, Ghosh, Yegneswaran
- CLEAR-DR: Interpretable Computer Aided Diagnosis of Diabetic Retinopathy. Kumar, Taylor, Wong
- Manipulating and Measuring Model Interpretability. Poursabzi-Sangdeh, Goldstein, Hofman,Wortman Vaughan, Wallach
12:00 PM -- Poster session part (all posters)
12.30 PM - 14.00 PM -- Lunch break
AFTERNOON SESSION
2:00 PM -- Invited talk: When the classifier doesn't know: optimum reject options for classification. BARBARA HAMMER
2:35 PM -- Contributed talk: Predict Responsibly: Increasing Fairness by Learning To Defer. Madras, Zemel, Pitassi
2:45 PM -- Contributed talk: Deep Motif Dashboard: Visualizing and Understanding Genomic Sequences Using Deep Neural Networks. Lanchantin, Singh, Wang, Qi
2:55 PM -- Announcement: BEST PAPER PRIZE
3:00 PM -- Coffee Break and Poster session part II (all posters)
4:05 PM -- Invited talk: Robot Transparency as Optimal Control. ANCA DRAGAN
4:40 PM -- Panel discussion
- SUCHI SARIA - Assistant Professor, Johns Hopkins University
- FINALE DOSHI-VELEZ - Assistant Professor of Computer Science, Harvard
- ADRIAN WELLER - Computational and Biological Learning Lab University of Cambridge and Alan Turing Institute
- BARBARA HAMMER - Professor oat CITEC centre of excellence, Bielefeld University
- ANCA DRAGAN - Assistant Professor, UC Berkeley
5:20 PM -- Final remarks
5:30 PM -- End of the day