Deep neural networks are frequently used by autonomous systems for their ability to learn complex, non-linear data patterns and make accurate predictions in dynamic environments. However, their use as black boxes introduces risks as the confidence in each prediction is unknown. Different frameworks have been proposed to compute accurate confidence measures along with the predictions but at the same time introduce a number of limitations like execution time overhead or inability to be used with high-dimensional data. In this paper, we use the Inductive Venn Predictors framework for computing probability intervals regarding the correctness of each prediction in real-time. We propose taxonomies based on distance metric learning to compute informative probability intervals in applications involving high-dimensional inputs. Empirical evaluation on image classification and botnet attacks detection in Internet-of-Things (IoT) applications demonstrates improved accuracy and calibration. The proposed method is computationally efficient, and therefore, can be used in real-time.
翻译:深神经网络经常被自主系统用来学习复杂、非线性数据模式和在动态环境中作出准确预测的能力,但是,它们作为黑盒的使用带来风险,因为对每项预测的信心尚不清楚。提出了不同的框架来计算准确的建立信任措施和预测,但同时也提出了若干限制,如执行时间管理或无法使用高维数据。在本文中,我们使用“导电文预测”框架来计算实时每项预测正确性的概率间隔。我们提议根据远程计量学习进行分类,以计算高维投入应用中的信息概率间隔。对图像分类的实证评估以及在互联网图灵应用中检测到的机器人网络攻击显示,精确度和校准率提高。拟议方法在计算上效率很高,因此可以实时使用。