156 XAI with Alexander Dolk (Swe)

In this episode we are discussing Alexander Dolks research paper about interpretable artificial intelligence. What is interpretable artificial intelligence, and what can it help us with?

Please note: When Alexander is describing the “traditional” training process for machine learning models he is referring to supervised machine learning models. A correction to the description is that it is the training set and the validation set that is used during the training process. The test set is kept separate from the training process and is used to test the model after training.