Batch-wise Regularization of Deep Neural Networks for Interpretability

Burkart, NadiaNadiaBurkartFaller, Philipp M.Philipp M.FallerPeinsipp, ElisabethElisabethPeinsippHuber, MarcoMarcoHuber2022-03-142022-03-142020https://publica.fraunhofer.de/handle/publica/40910410.1109/MFI49285.2020.9235209Fast progress in the field of Machine Learning and Deep Learning strongly influences the research in many application domains like autonomous driving or health care. In this paper, we propose a batch-wise regularization technique to enhance the interpretability for deep neural networks (NN) by means of a global surrogate rule list. For this purpose, we introduce a novel regularization approach that yields a differentiable penalty term. Compared to other regularization approaches, our approach avoids repeated creating of surrogate models during training of the NN. The experiments show that the proposed approach has a high fidelity to the main model and also results in interpretable and more accurate models compared to some of the baselines.enExplainable Artificial Intelligence (XAI)Künstliche Intelligenzmaschinelles Lernenneuronales Netz004670Batch-wise Regularization of Deep Neural Networks for Interpretabilityconference paper