Testing (with) Artificial Intelligence

About

Judgement day is near! Or at least that's what most people think when they hear about AI. The most important thing you should now is that AI is nothing more than a computer system solving problems usually solved by humans. AI can be used in a lot of different domains: not only self-driving cars, chatbots and deepfakes, but also... testing!

One of the major challenges with AI is knowing whether the AI system has been trained properly. To answer this question, the AI system has to be tested. Not only to see whether it has been properly trained, but also to assess whether the learned can be applied in the real world.

In this session you will get a brief introduction on testing of AI systems. What are the differences with non-AI software systems? What are the possible (new) risks with AI systems and what should you do to mitigate these? On top of that, you will get a peek preview of how AI could be used to facilitate your testing. Like most AI systems, there is still a long way to go, but the destination is very promising!