Despite the successes in many fields, it is found that neural networks are difficult to be both accurate and robust, i.e., high accuracy networks are often vulnerable. Various empirical and analytic studies have substantiated that there is more or less a trade-off between the accuracy and robustness of neural networks. If the property is inherent, applications based on the neural networks are vulnerable with untrustworthy predictions. To more deeply explore and understand this issue, in this study we show that the accuracy-robustness trade-off is an intrinsic property whose underlying mechanism is closely related to the uncertainty principle in quantum mechanics. By relating the loss function in neural networks to the wave function in quantum mechanics, we show that the inputs and their conjugates cannot be resolved by a neural network simultaneously. This work thus provides an insightful explanation for the inevitability of the accuracy-robustness dilemma for general deep networks from an entirely new perspective, and furthermore, reveals a potential possibility to study various properties of neural networks with the mature mathematical tools in quantum physics.
翻译:尽管在许多领域取得了成功,但人们发现,神经网络很难做到准确和稳健,也就是说,高度精确的网络往往很脆弱。各种经验和分析研究证实,神经网络的准确性和稳健性之间有或多或少的权衡。如果该属性是内在的,基于神经网络的应用很脆弱,预测不可信。为了更深入地探讨和理解这一问题,我们在本研究报告中表明,精确-紫色交易是一种内在属性,其基本机制与量子力学的不确定性原则密切相关。通过将神经网络的损失功能与量子力学中的波函数联系起来,我们表明,输入及其共性不能同时由神经网络解决。因此,这项工作从全新的角度对一般深层网络的精准性-紫色性两难情况提供了深刻的深刻解释。此外,我们揭示了用成熟的数学工具研究神经网络的各种特性的可能性。