no code implementations • 6 Jun 2023 • Ikboljon Sobirov, Cheng Xie, Muhammad Siddique, Parijat Patel, Kenneth Chan, Thomas Halborg, Christos Kotanidis, Zarqiash Fatima, Henry West, Keith Channon, Stefan Neubauer, Charalambos Antoniades, Mohammad Yaqub
Since the emergence of convolutional neural networks (CNNs), and later vision transformers (ViTs), the common paradigm for model development has always been using a set of identical block types with varying parameters/hyper-parameters.