1. Introduction
What we call deep learning today descends from the connectionist approach to cognitive science [39, 8]—a paradigm reflecting the hypothesis that how computational networks are wired is crucial for building intelligent machines. Echoing this perspective, recent advances in computer vision have been driven by moving from models with chain-like wiring [20, 55, 43, 44] to more elaborate connectivity patterns, ., ResNet [12] and DenseNet [17], that are effective in large part because of how they are wired.