CfP: Minds & Machines Special Issue on "Machine Learning: Prediction Without Explanation?"
Machine Learning: Prediction Without Explanation? https://www.springer.com/ journal/11023/updates/18180316 Description Over the last decades, Machine Learning (ML) techniques have gained central prominence in many areas of science. ML typically aims at pattern recognition and prediction, and in many cases has become a better tool for these purposes than traditional methods. The downside, however, is that ML does not seem to provide any explanations, at least not in the same sense as theories or traditional models do. This apparent lack of explanation is often also linked to the opacity of ML techniques, sometimes referred to as the ‘Black Box Challenge’. Methods such as heat maps or adversarial examples are aimed at reducing this opacity and opening the black box. But at present, it remains an open question how and what exactly these methods explain and what the nature of these explanations is. While in some areas of science this may not create any interesting philosop...