Our paper titled “Circumventing the solution of inverse problems in mechanics through deep learning: application to elasticity imaging” has been accepted for publication in Journal of Computer Methods in Applied Mechanics and Engineering (CMAME). In this paper we demonstrate the role of deep learning in classifying specimen based on their elastic heterogeneity and non-linearity, while circumventing the need to solve a complex inverse elasticity problem. In the process we also showcase the use of domain randomization in medical imaging, where we demonstrate how physics-based modeling can facilitate transfer learning in data-scarce medical imaging applications. By analyzing the learned filters, we reveal interesting connection between this deep learning-based elasticity imaging method to traditional strain imaging methods. More work on use of deep learning for efficient solution of inverse problems in progress!