Bort：有界正交约束的可解释神经网络
Bort: Towards Explainable Neural Networks with Bounded Orthogonal Constraint
摘要：
深度学习已经彻底改变了人类社会，但深度神经网络的黑盒性质阻碍了其在可靠性要求较高的行业中的进一步应用。为了解开它们，许多作品观察或影响内部变量，以提高黑箱模型的可理解性和可逆性。然而，现有的方法依赖于直观的假设，缺乏数学保证。为了弥合这一差距，我们引入了Bort，一个优化器，用于提高模型的可解释性与模型参数的有界性和正交性约束，来自模型的可理解性和可逆性的充分条件。我们对Bort优化的模型表示进行重建和回溯，并观察到模型可解释性的明显改善。基于Bort，我们能够合成可解释的对抗样本，而无需额外的参数和训练。令人惊讶的是，我们发现Bort不断提高各种架构的分类准确性，包括MNIST，CIFAR-10和ImageNet上的ResNet和DeiT。代码：https://github.com/zbr17/Bort.
英文摘要：
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 comprehensibility and invertibility of the black-box models. 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 invertibility. We perform reconstruction and backtracking on the model representations optimized by Bort and observe a clear 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. Code: https://github.com/zbr17/Bort.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
