Data Sanity Check for Deep Learning Systems via Learnt Assertions

no code implementations • 6 Sep 2019 • Haochuan Lu, Huanlin Xu, Nana Liu, Yangfan Zhou, Xin Wang

But the statistical nature of DL makes it quite vulnerable to invalid inputs, i. e., those cases that are not considered in the training phase of a DL model.

Detecting Deep Neural Network Defects with Data Flow Analysis

no code implementations • 5 Sep 2019 • Jiazhen Gu, Huanlin Xu, Yangfan Zhou, Xin Wang, Hui Xu, Michael Lyu

Deep neural networks (DNNs) are shown to be promising solutions in many challenging artificial intelligence tasks.

Object Recognition