Deep-learning is applied to play the game in some projects, so it should make sense to apply it for UI test automation. Any comments on this idea?
Automated input systems are widely used for large-scale dynamic analysis and for the testing of mobile applications. Such input systems have to constantly choose which UI element to interact with and how to interact with it, in order to achieve high coverage with a limited time budget.
You can refer to the following research papers for a better understanding of the role of Deep Learning in the UI test automation: