EDGE HORIZON | 1 Million Point Loss Landscape | Gradient Descent | Deep Learning

EDGE HORIZON visualizes a loss landscape in extreme resolution, using 1 million loss points captured during the training of a convnet. The morphology of the landscape during the training phase is influenced by the parameters of the network. More details and related analysis about this and other visualizations will be published in the future. Loss Landscape generated with real data: Convnet, imagenette dataset, sgd-adam, bs=16, bn, lr sched, train mod, 1 million pts, 0.5 w range, 20p-interp, log scaled (ori