The output of the convolutional layer is usually handed in the ReLU activation purpose to bring non-linearity to the model. It will take the function map and replaces all the damaging values with zero. * One other websites referenced on this site are owned and operated by their respective https://financefeeds.com/ai-growth-to-triple-us-data-center-usage-by-2030-as-us-quits-paris-agreement/