Seems like the implementation on Laplace Activation deviates from what the paper described:
In the paper, I think it should write std = 1 / math.sqrt(4 * math.pi) instead of std = math.sqrt(0.25 * math.pi) as the former one is an approximation of relu^2
Seems like the implementation on Laplace Activation deviates from what the paper described: In the paper, I think it should write
std = 1 / math.sqrt(4 * math.pi)
instead ofstd = math.sqrt(0.25 * math.pi)
as the former one is an approximation of relu^2