Inductive Programming as Approach to Comprehensible Machine Learning

In the early days of machine learning, Donald Michie introduced two orthogonal dimensions to evaluate performance of machine learning approaches – predictive accuracy and comprehensibility of the learned hypotheses. Later definitions narrowed the focus to measures of accuracy. As a consequence, statistical/neuronal approaches have been favoured over symbolic approaches to machine learning, such as inductive logic programming (ILP). Recently, the importance of comprehensibility has been rediscovered under the slogan ‘explainable AI’. This is due to the growing interest in black-box deep learning approaches in many application domains where it is crucial that system decisions are transparent and comprehensible and in consequence trustworthy. I will give a short history of machine learning research followed by a presentation of two specific approaches of symbolic machine learning – inductive logic programming and end-user programming. Furthermore, I will present current work on explanation generation. Die Arbeitsweise der Algorithmen, die über uns entscheiden, muss transparent gemacht werden, und wir müssen die Möglichkeit bekommen, die Algorithmen zu beeinflussen. Dazu ist es unbedingt notwendig, dass die Algorithmen ihre Entscheidung begründen! Peter Arbeitsloser zu John of Us, Qualityland, Marc-Uwe Kling, 2017