Deep learning has revolutionized human society, yet the black-box nature of deep neural networks hinders further application to reliability-demanded industries. In the attempt to unpack them, many works observe or impact internal variables to improve the model's comprehensibility and transparency. However, existing methods rely on intuitive assumptions and lack mathematical guarantees. To bridge this gap, we introduce Bort, an optimizer for improving model explainability with boundedness and orthogonality constraints on model parameters, derived from the sufficient conditions of model comprehensibility and transparency. We perform reconstruction and backtracking on the model representations optimized by Bort and observe an evident improvement in model explainability. Based on Bort, we are able to synthesize explainable adversarial samples without additional parameters and training. Surprisingly, we find Bort constantly improves the classification accuracy of various architectures including ResNet and DeiT on MNIST, CIFAR-10, and ImageNet.

本研究介绍了一种名为 Bort 的优化器，它通过对模型参数设置有限制条件来提高深度学习模型的可解释性并进行反演。实验表明，在 Bort 的优化下，模型的可解释性得到了显著提高，并且能够在不使用附加参数和训练的情况下合成出可解释的对抗样本。更出乎意料的是，Bort 还能不断提高各种结构的模型在 MNIST、CIFAR-10 和 ImageNet 上的分类准确率。

Bort: 具有有界正交约束的可解释神经网络