Beyond holography: the entropic quantum gravity foundations of image processing

Recently, thanks to the development of artificial intelligence (AI) there is increasing scientific attention to establishing the connections between theoretical physics and AI. Traditionally, these connections have been focusing mostly on the relation between string theory and image processing and involve important theoretical paradigms such as holography. Recently G. Bianconi has proposed the entropic quantum gravity approach that proposes an action for gravity given by the quantum relative entropy between the metrics associated to a manifold. Here it is demonstrated that the famous Perona-Malik algorithm for image processing is the gradient flow of the entropic quantum gravity action. These results provide the geometrical and information theory foundations for the Perona-Malik algorithm and open new avenues for establishing fundamental relations between brain research, machine learning and entropic quantum gravity.