Fraunhofer-Institut für Optronik, Systemtechnik und Bildauswertung IOSB

Filters

2
2
Reset filters

Settings
Now showing 1 - 2 of 2
  • Publication
    Batch-wise Regularization of Deep Neural Networks for Interpretability
    ( 2020)
    Burkart, Nadia
    ;
    Faller, Philipp M.
    ;
    Peinsipp, Elisabeth
    ;
    Huber, Marco
    Fast 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.
  • Publication
    Forcing Interpretability for Deep Neural Networks through Rule-based Regularization
    ( 2019)
    Burkart, Nadia
    ;
    Huber, Marco
    ;
    Faller, Philipp M.
    Remarkable progress in the field of machine learning strongly drives the research in many application domains. For some domains, it is mandatory that the output of machine learning algorithms needs to be interpretable. In this paper, we propose a rule-based regularization technique to enforce interpretability for neural networks (NN). For this purpose, we train a rule-based surrogate model simultaneously with the NN. From the surrogate, a metric quantifying its degree of explainability is derived and fed back to the training of the NN as a regularization term. We evaluate our model on four datasets and compare it to unregularized models as well as a decision tree (DT) based baseline. The rule-based regularization approach achieves interpretability and competitive accuracy.