Learning symbolic features for rule induction in computer aided diagnosis

In computer aided medical diagnosis (CAD), interpretability of learned models is an important concern. Unfortunately, the raw data used to train a model are often in subsymbolic form (for instance, images), which makes the application of symbolic learning methods difficult. Construction of symbolic features can bridge the gap between the symbolic and subsymbolic level. This paper presents a case study of how ILP learners can be used to learn models from visual data by using a feature construction step. The resulting model has an accuracy comparable to that of previous models, but better interpretability.

Publication year:2014

Accessibility:Open