School of Computer Science, Chengdu University, Chengdu, China.
Department of Mathematics, Government College University Faisalabad, Faisalabad 38000, Pakistan.
Comput Intell Neurosci. 2022 Oct 7;2022:9051908. doi: 10.1155/2022/9051908. eCollection 2022.
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.
深度神经网络有多个层次，可以学习更复杂的模式，并被构建为模拟人类大脑的活动。目前，它为图像识别、语音识别和自然语言处理中的许多问题提供了最佳解决方案。本研究涉及深度神经网络的拓扑性质。拓扑指数是与网络连通性相关的数值量，与网络输出的效率和准确性相关。在这项研究中，计算了具有有限数量隐藏层的深度神经网络的不同度相关拓扑指数，如扎格指数、兰迪指数、原子键连接指数、几何算术指数、遗忘指数、多个扎格指数和超扎格指数。
