Computational efficiency and adversarial robustness are critical factors in real-world engineering applications. Yet, conventional neural networks often fall short in addressing both simultaneously, or even separately. Drawing insights from natural physical systems and existing literature, it is known that an input convex architecture enhances computational efficiency, while a Lipschitz-constrained architecture bolsters adversarial robustness. By leveraging the strengths of convexity and Lipschitz continuity, we develop a novel network architecture, termed Input Convex Lipschitz Recurrent Neural Network. This model outperforms existing recurrent units across a spectrum of engineering tasks in terms of computational efficiency and adversarial robustness. These tasks encompass a benchmark MNIST image classification, real-world solar irradiance prediction for Solar PV system planning at LHT Holdings in Singapore, and real-time Model Predictive Control optimization for a chemical reactor.

翻译：计算效率和对抗鲁棒性是实际工程应用中的关键因素。然而，传统神经网络通常难以同时满足这两个要求，甚至无法分别实现。通过对自然物理系统的洞察及现有文献的研究，已知输入凸架构能够提升计算效率，而Lipschitz约束架构则增强对抗鲁棒性。通过结合凸性与Lipschitz连续性的优势，我们提出了一种新型网络架构——输入凸Lipschitz循环神经网络。该模型在多项工程任务的计算效率和对抗鲁棒性方面均优于现有循环单元。这些任务涵盖基准MNIST图像分类、新加坡LHT Holdings公司太阳能光伏系统规划中的实际太阳辐照预测，以及化学反应器实时模型预测控制优化。