TY - JOUR
AU - V, Gayathiri
AU - A, Manimaran
PY - 2023/11/24
Y2 - 2024/06/13
TI - Computing Topological Indices of 3-Layered Artificial Neural Network
JF - Contemporary Mathematics
JA - Contemp. Math.
VL - 4
IS - 4
SE - Research Article
DO - 10.37256/cm.4420233502
UR - https://ojs.wiserpub.com/index.php/CM/article/view/3502
SP - 1135-1149
AB - <p>Let <em>η</em> be a network graph with vertex and edge sets <em>P(η)</em> and <em>E(η)</em>, respectively. This study aims to find the expected value (obtained during training and testing data) for Artificial Neural Networks (<em>ANN</em>) through indices. A three-layer artificial neural network is considered here, which we call <em>ANN(m, n, o)</em>. Moreover, a comparison is given between the topological indices (TI) of <em>ANN</em> with topological indices (TI) of the Probabilistic Neural Network (<em>PNN</em>). By comparing the indices, we can assess the effect of network structure on <em>ANN</em> model accuracy. The comparison between the two approaches helps us understand the accuracy and performance of <em>ANN</em> and<em> PNN</em> models. We can also gain insights into the differences between <em>ANN</em> and <em>PNN</em> in terms of their ability to learn and generalize.</p>
ER -