An Approach to Quantifying the Quality of Induced Theories

The quality of theories produced with the help of machine learning algorithmsis usually measured in terms of accuracy and coverage. This paperreopens the issue of understandability of induced theories, which, while prominentin the early days of ML, seems to have fallen from favor in the sequel.The guiding question is: beyond accuracy, what constitutes a good theory?An attempt at surveying relevant work in the fields of linguistics and cognitivepsychology is made. The sympathetic reader...