Computing Receptive Fields of Convolutional Neural Networks -- A new Distill article by André Araujo, Wade Norris, and Jack Sim.https://t.co/XqvDBlNBoM
— distillpub (@distillpub) November 4, 2019
Computing Receptive Fields of Convolutional Neural Networks -- A new Distill article by André Araujo, Wade Norris, and Jack Sim.https://t.co/XqvDBlNBoM
— distillpub (@distillpub) November 4, 2019
One under appreciated fact highlighted in this article: the theoretical receptive field of modern neural networks is *ridiculously* large. Often thousands of pixels, while the input image ins only hundreds. https://t.co/WQiMnG8v8w
— Chris Olah (@ch402) November 4, 2019