Description (Presentation files available in Links below)
|7:30-8:30||Registration – AAAI-19 Badge Pickup and Onsite Registration in The Coral Lounge on the sixth floor of the Mid Pacific Conference Center.|
|8:30-8:35||Welcome and Introduction|
|8:35-9:20||Keynote 1: Dr. Sandeep Neema (DARPA), Assured Autonomy|
Session 1: Safe Planning and Operation of Autonomous Systems – Chair: Huáscar Espinoza
– Minimizing the Negative Side Effects of Planning with Reduced Models, Sandhya Saisubramanian and Shlomo Zilberstein.
Poster Pitches 1 – (2 mins x pitch)
– Towards international standards for evaluating machine learning, Frank Rudzicz, P Alison Paprica and Marta Janczarski.
|10:30-11:00||Poster Sessions and Coffee Break|
|11:00-11:20||Invited Talk: Dr. Peter Eckersley (Partnership on AI), Impossibility and Uncertainty Theorems in AI Value Alignment (or why your AGI should not have a utility function)|
Session 2: New Paradigms in AI and AGI Safety – Chair: José Hernández-Orallo
– Towards Robust End-to-End Alignment, Lê Nguyên Hoang.
|12:00-12:20||Invited Talk: Prof. Alessio R. Lomuscio (Imperial College London), Reachability Analysis for Neural Agent-Environment Systems|
Session 3: Safety in Automated Driving – Chair: Mauricio Castillo-Effen
– How Many Operational Design Domains, Objects, and Events?, Philip Koopman and Frank Fratrik.
|13:00-14:00||Poster Sessions and Lunch (on your own; no sponsored lunch provided)|
|14:00-14:45||Keynote 2: Prof. Francesca Rossi (IBM and University of Padova), Ethically Bounded AI|
Session 4: Safety-Related AI Requirements and Characteristics – Chair: François Terrier
– Requirements Assurance in Machine Learning, Alec Banks and Rob Ashmore.
Poster Pitches 2 – (2 mins x pitch)
– Temporally Extended Metrics for Markov Decision Processes, Philip Amortila, Marc G. Bellemare, Prakash Panangaden and Doina Precup.
|15:35-16:00||Poster Sessions and Coffee Break|
|16:00-16:20||Invited Talk: Dr. Ian Goodfellow (Google Brain), Adversarial Robustness for AI Safety|
Session 5: Adversarial Machine Learning – Chair: Xiaowei Huang
– Detecting Backdoor Attacks on Deep Neural Networks by Activation Clustering, Bryant Chen, Wilka Carvalho, Nathalie Baracaldo, Heiko Ludwig, Benjamin Edwards, Taesung Lee, Ian Molloy and Biplav Srivastava. [Best Paper Award]
|17:20-17:30||Wrap-up and Best Paper Award|