While talking about the batch norm, two new parameters were introduced - gamma and beta, which allow us to control the mean and variance of the intermediary inputs (Z[l] values for any layer “l”).
So, these 2 parameters are just a single value for each hidden layer, right? (and not n[l] distinct values)
Later in a lecture, the dimensions for these two parameters were given as (n[l],1). So I am assuming they are a single value that will be broadcasted to arrays of this dimension. Am I correct?