Joshua ThompsoninTowards Data ScienceOn the Disparity Between Swish and GELUWhy two similar functions can produce very different outcomesMar 3, 20211Mar 3, 20211
Joshua ThompsoninTowards Data ScienceVisualizing the MLP: A Composition of TransformationsHow to draw a nonlinear decision boundaryFeb 19, 2021Feb 19, 2021