- What are the common or different things in traditional testing vs DL testing? Coverage criteria, mutation operators and so on.
What is the best coverage criteria?
What is the most effective mutation operators?
Regression testing has long been studied in “traditional” software systems. What does regression testing mean when I have a ML based system?
What is a regression bug?
- How to test or analyse different types of networks like FNN/RNN/DRL? What are the common methods we can follow, and what are the adaptations we need?
-
How to apply testing/analysis in different applications domains? For example in DL based code analysis, security solutions (malware detection or network intrustion detections)
-
Techniques have been proposed to repair a deep neural network (e.g., by modifying the weights). In what scenarios or tasks do you think are such techniques more applicable?
-
How to achieve model interpretability? Examples like making surrogate models (e.g. in LIME), or a gradient based approach, as in Integrated Gradients, or a global approach such as rule induction.
Fri 16 JulDisplayed time zone: Brussels, Copenhagen, Madrid, Paris change
03:20 - 04:00 | Testing/Analysis and ML/DL 1 Discussions with Experts at Discussions with Experts (room 1) Chair(s): Satish Chandra Facebook, Yang Liu Nanyang Technological University We will be discussing:
… | ||
03:20 40mPanel | Testing/Analysis and ML/DL 1 Discussions with Experts | ||