Computing Topological Invariants of Deep Neural Networks. (7th October 2022)

• Record Type: Journal Article
• Authors: Zhang, Xiujun; Idrees, Nazeran; Kanwal, Salma; Saif, Muhammad Jawwad; Saeed, Fatima
• Other Names: Ding Baiyuan Academic Editor.
• Is Part Of: Computational intelligence and neuroscience. Volume 2022(2022)
• Publication Date: 2022-10-07
• Subjects: Neurosciences -- Data processing -- Periodicals; Computational intelligence -- Periodicals; Computational neuroscience -- Periodicals; 612.80285
• DOI: 10.1155/2022/9051908
• Languages: English
• ISSNs: 1687-5265

Abstract

Abstract : A deep neural network has multiple layers to learn more complex patterns and is built to simulate the activity of the human brain. Currently, it provides the best solutions to many problems in image recognition, speech recognition, and natural language processing. The present study deals with the topological properties of deep neural networks. The topological index is a numeric quantity associated to the connectivity of the network and is correlated to the efficiency and accuracy of the output of the network. Different degree-related topological indices such as Zagreb index, Randic index, atom-bond connectivity index, geometric-arithmetic index, forgotten index, multiple Zagreb indices, and hyper-Zagreb index of deep neural network with a finite number of hidden layers are computed in this study.