SCHEDULE.
8:30-8:50: Registration
8:50-9:00
Welcome session
9:00-10:00
Invited talk: Policy Synthesis for Uncertain Autonomous Robots
Swarat Chaudhuri, Rice University
10:00-10:30: Coffee Break
10:30-10:54: Reasoning about Convolutional Neural Networks via Transfer Learning and Convex Programming
Dario Guidotti, Francesco Leofante, Luca Pulina and Armando Tacchella
10:54-11:18: Verification of RNN-Based Neural Agent-Environment Systems
Michael Akintunde, Andreea Kovorchian, Alessio Lomuscio and Edoardo Pirovano
11:18-11:42: Improving Deep Neural Network Verification Using Specification-Guided Search
Joshua Smith, Xiaowei Huang, Viswanathan Swaminathan and Zhen Zhang [Slides]
11:42-12:06: Logic extraction for Explainable AI
Susmit Jha [Slides]
12:06-12:30: The Marabou Framework for Verification and Analysis of Deep Neural Networks
Guy Katz, Derek Huang, Duligur Ibeling, Kyle Julian, Christopher Lazarus, Rachel Lim, Parth Shah, Shantanu Thakoor, Haoze Wu, Aleksandar Zeljic, David Dill, Mykel Kochenderfer and Clark Barrett
12:30-14:30: Lunch
​14:30-14:54: Conformal Predictions for Hybrid System State Classification
Luca Bortolussi, Francesca Cairoli, Nicola Paoletti, Scott Smolka and Scott Stoller [Slides]
14:54-15:18: Formal verification of neural network controlled autonomous systems
Xiaowu Sun, Haitham Khedr and Yasser Shoukry [Slides]
​15:18-15:42: Safety Verification in Reinforcement Learning Control
Hoang Dung Tran, Feiyang Cai, Diego Manzanas Lopez, Patrick Musau, Taylor T Johnson and Xenofon Koutsoukos [Slides]
​15:42-16:00: Discussion: VNNLIB
​
16:00-16:30: Coffee Break
16:30-16:54: Better AI through Logical Scaffolding
Nikos Arechiga, Jonathan DeCastro, Soonho Kong and Karen Leung
16:54-17:20: Panel discussion: Formal Methods and Machine Learning: Progress and Future directions
Clark Barrett, Taylor T. Johnson, Alessio Lomuscio and Luca Pulina
17:20-17:30: Concluding remarks
​