论文标题
神经网络的样本特异性输出约束
Sample-Specific Output Constraints for Neural Networks
论文作者
论文摘要
神经网络在各种学习任务中达到最先进的表现。但是，缺乏理解决策过程会导致外观作为黑匣子。我们解决了这一点，并提出了约束网络，这是一个神经网络，具有通过额外输入来限制每个正向传递空间的能力。约束网络的预测在指定的域中得到了证明。这使ConstraintNet能够明确排除意外甚至危险的输出，而最终预测仍然是从数据中学到的。我们专注于凸多属的形式的约束，并显示对进一步限制类别的概括。可以通过修改现有的神经网络体系结构来轻松构建约束网。我们强调，ConstraintNet是端到端可训练的，在前和向后没有没有开销。出于插图目的，我们通过修改CNN并为面部地标预测任务构建约束来建模。此外，我们证明了对车辆的关注对象控制器的应用，作为安全至关重要的应用。我们提交了一种方法和系统，用于基于Derman Ptarent和商标办公室基于约束网的实体生成安全关键产出的方法和系统。
Neural networks reach state-of-the-art performance in a variety of learning tasks. However, a lack of understanding the decision making process yields to an appearance as black box. We address this and propose ConstraintNet, a neural network with the capability to constrain the output space in each forward pass via an additional input. The prediction of ConstraintNet is proven within the specified domain. This enables ConstraintNet to exclude unintended or even hazardous outputs explicitly whereas the final prediction is still learned from data. We focus on constraints in form of convex polytopes and show the generalization to further classes of constraints. ConstraintNet can be constructed easily by modifying existing neural network architectures. We highlight that ConstraintNet is end-to-end trainable with no overhead in the forward and backward pass. For illustration purposes, we model ConstraintNet by modifying a CNN and construct constraints for facial landmark prediction tasks. Furthermore, we demonstrate the application to a follow object controller for vehicles as a safety-critical application. We submitted an approach and system for the generation of safety-critical outputs of an entity based on ConstraintNet at the German Patent and Trademark Office with the official registration mark DE10 2019 119 739.
