Optimizing caching locations of popular content has received significant research attention over the last few years. This paper targets the optimization of the caching locations by proposing a novel transformation of the optimization problem to a grey-scale image that is applied to a deep convolutional neural network (CNN). The rational for the proposed modeling comes from CNN's superiority to capture features in gray-scale images reaching human level performance in image recognition problems. The CNN has been trained with optimal solutions and the numerical investigations and analyses demonstrate the promising performance of the proposed method. Therefore, for enabling real-time decision making we moving away from a strictly optimization based framework to an amalgamation of optimization with a data driven approach.