Paluzo-Hidalgo Eduardo, Gonzalez-Diaz Rocio, Gutiérrez-Naranjo Miguel A, Heras Jónathan
Department of Applied Mathematics I, University of Sevilla, 41012 Sevilla, Spain.
Department of Computer Sciences and Artificial Intelligence, University of Sevilla, 41012 Sevilla, Spain.
J Imaging. 2021 Sep 1;7(9):173. doi: 10.3390/jimaging7090173.
Simplicial-map neural networks are a recent neural network architecture induced by simplicial maps defined between simplicial complexes. It has been proved that simplicial-map neural networks are universal approximators and that they can be refined to be robust to adversarial attacks. In this paper, the refinement toward robustness is optimized by reducing the number of simplices (i.e., nodes) needed. We have shown experimentally that such a refined neural network is equivalent to the original network as a classification tool but requires much less storage.
单纯映射神经网络是一种最近由单纯复形之间定义的单纯映射所诱导的神经网络架构。已经证明，单纯映射神经网络是通用逼近器，并且可以进行改进以使其对对抗性攻击具有鲁棒性。在本文中，通过减少所需的单纯形（即节点）数量来优化对鲁棒性的改进。我们通过实验表明，这样一个经过改进的神经网络作为分类工具与原始网络等效，但所需的存储要少得多。
