Abstract: Conventional empirical constitutive models often fail to describe complex material behaviour accurately. To address this difficulty, the feasibility and engineering significance of nesting artificial neural networks(ANNs) within finite element analysis(FEA) are investigated. This paper reviews the concept of machine learning nested in FEA, focusing on ANN-based constitutive modelling, the challenges in nested training and backpropagation, and the contributions of the authors. These studies show that nesting ANNs within FEA enables continuous model updating under physical constraints, using structural- or process-level measurements to update the model. The updated models show improved agreement between numerical predictions and experimental observations. The nested ANN–FEA framework provides an engineering-feasible approach for data-driven constitutive modelling and digital twin development. It shows strong potential for complex materials and multiphysics applications.