There’s also the “Plato’s man” type of problem where undesirable things fall under the advanced definition of interpretability. For example, ordinary neural nets are “interpretable,” because they are merely made out of interpretable components (simple matrices with a non-linearity) glued together.
There’s also the “Plato’s man” type of problem where undesirable things fall under the advanced definition of interpretability. For example, ordinary neural nets are “interpretable,” because they are merely made out of interpretable components (simple matrices with a non-linearity) glued together.