Cognitive Machine Learning (1): Learning to Explain

Explanation has always been a core topic in machine learning and artificial intelligence. We constantly seek new tools to derive and develop machine learning systems that offer a spectrum of explanations, knowing that different types of explanations are possible; valid or not, we will tend to hold the explanatory requirements of our machine learning systems to a higher standard than we hold ourselves. Learning to explain then becomes a central research question.

Source: Cognitive Machine Learning (1): Learning to Explain ← The Spectator