Unveiling and Mitigating Generalized Biases of DNNs through the Intrinsic Dimensions of Perceptual Manifolds

arXiv:2404.13859v1 Announce Type: new
Abstract: Building fair deep neural networks (DNNs) is a crucial step towards achieving trustworthy artificial intelligence. Delving into deeper factors that affect the fairness of DNNs is paramount and serves as the foundation for mitigating model biases. However, current methods are limited in accurately predicting DNN biases, relying solely on the number of training samples and lacking more precise measurement tools. Here, we establish a geometric perspective for analyzing the fairness of DNNs, comprehensively exploring how …

abstract artificial artificial intelligence arxiv biases building cs.ai cs.cv current dimensions fair fairness foundation generalized however intelligence intrinsic networks neural networks through trustworthy type