The recent years have witnessed the rise of accurate but obscure decision systems which hide the logic of their internal decision processes to the users. The lack of...

MARLENA is novel technique able to explain the reasons behind any black-box multi-label classifier decision. It will generate an explanation in the form of a decision rule....

The yeast dataset is a collection of yeast microarray expressions and phylogenetic profiles which can be used to learn the yeast gene functional categories. One row of this...

The medical dataset contains a corpus of fully anonymized clinical text. Each document in the corpus is associated with a set of ICD-9 codes which represents the diagnosis...

In the german credit dataset each one of the 1,000 persons is classified as a good or bad creditor according to attributes like age, sex, checking_account, credit_amount,...

The compas dataset contains the features used by the COMPAS algorithm for scoring defendants and their risk (Low, Medium and High), for over $4,000$ individuals. We considered...

The adult dataset includes $48,842$ instances with demographic information like age, workclass, marital-status, race, capital-loss, capital-gain etc. The income attribute...