Blogs (1) >>
ASE 2019
Sun 10 - Fri 15 November 2019 San Diego, California, United States
Thu 14 Nov 2019 11:20 - 11:40 at Cortez 2&3 - Deep Models Chair(s): Nazareno Aguirre

We present techniques for automatically inferring formal properties of feed-forward neural networks. We observe that a significant part (if not all) of the logic of feed forward networks is captured in the activation status (on or off) of its neurons. We propose to extract patterns based on neuron decisions as preconditions that imply certain desirable output property e.g., the prediction being a certain class. Together, the inferred preconditions and the output property form a {\em contract} for the network. We present techniques to extract input properties} encoding convex predicates on the input space that imply given output properties and layer properties, representing network properties captured in the hidden layers that imply the desired output behavior. We apply our techniques on networks for the MNIST and ACASXU applications. Our experiments highlight the use of the inferred properties in a variety of tasks, such as explaining predictions, providing robustness guarantees, simplifying proofs, and network distillation.

Thu 14 Nov
Times are displayed in time zone: (GMT-07:00) Tijuana, Baja California change

ase-2019-paper-presentations
10:40 - 12:20: Papers - Deep Models at Cortez 2&3
Chair(s): Nazareno AguirreDept. of Computer Science FCEFQyN, University of Rio Cuarto
ase-2019-papers10:40 - 11:00
Talk
Yan ZhengTianjin University, Xiaofei XieNanyang Technological University, Ting SuETH Zurich, Lei MaKyushu University, Jianye HaoTianjin University, Zhaopeng MengTianjin University, Yang LiuNanyang Technological University, Singapore, Ruimin ShenFuxi AI Lab in Netease, Yinfeng ChenFuxi AI Lab in Netease, Changjie FanFuxi AI Lab in Netease
Link to publication Pre-print
ase-2019-papers11:00 - 11:20
Talk
Mahdi NejadgholiConcordia University, Jinqiu YangConcordia University, Montreal, Canada
ase-2019-papers11:20 - 11:40
Talk
Divya GopinathCarnegie Mellon University, Hayes ConverseThe University of Texas at Austin, Corina S. PasareanuCarnegie Mellon University Silicon Valley, NASA Ames Research Center, Ankur TalyGoogle
ase-2019-papers11:40 - 12:00
Talk
Qianyu GuoTianjin University, Sen ChenNanyang Technological University, Singapore, Xiaofei XieNanyang Technological University, Lei MaKyushu University, Qiang HuKyushu University, Japan, Hongtao LiuTianjin University, Yang LiuNanyang Technological University, Singapore, Jianjun ZhaoKyushu University, Li XiaohongTianJin University
Pre-print
ase-2019-Demonstrations12:00 - 12:10
Demonstration
Qiang HuKyushu University, Japan, Lei MaKyushu University, Xiaofei XieNanyang Technological University, Bing YuKyushu University, Japan, Yang LiuNanyang Technological University, Singapore, Jianjun ZhaoKyushu University
ase-2019-Demonstrations12:10 - 12:20
Demonstration
Xiaofei XieNanyang Technological University, Hongxu ChenNanyang Technological University, Yi LiNanyang Technological University, Lei MaKyushu University, Yang LiuNanyang Technological University, Singapore, Jianjun ZhaoKyushu University