In the first part of my talk I will show how complex visual inference tasks can be performed with Deep-Learning, in a totally unsupervised way, by training on a single image -- the test image alone. The strong recurrence of information inside a single natural image provides powerful internal examples which suffice for self-supervision of Deep-Networks, without any prior examples or training data. This new paradigm gives rise to true “Zero-Shot Learning”. I will show the power of this approach to a variety of visual tasks, including super-resolution, image-segmentation, transparent layer separation, image-dehazing, and more. In the second part of my talk I will show how self-supervision can be used for “Mind-Reading” (recovering observed visual information from fMRI brain recordings), when only very few fMRI training examples are available.