Eric2Hamel
Eric2Hamel
Scipy stats reciprocal is really a log-uniform, but they parametrize it differently than us. The way we parametrize it is that we output directly the min and max in the...
Why did you use the inverse in your plot? What is the difference between True Histogram and smoothed? Not sure to correctly understand what you are testing in your plot....
What is the reason to calculate the metric before the first epoch?
As the Boolean and Bernouilli it depends on what is easier for user. It could be possible in the code to just do Bernouilli = Boolean so the two name...
Not sure if it is worth inheriting Boolean(Bernoulli) since Boolean is Bernoulli (really the same thing). So not sure the inheritance is worth it. But I aggree for class Binomial(Choice)...
What you are refining to with `10**uniform(-2,-4)` is in fact a logUniform (with base 10) distribution. Neuraxle currently have a logUniform but using a base 2 which means `2**uniform(a, b)`....
@guillaume-chevalier : Your right, putting it in base 2 or base 10 will still give something uniform. The only thing it matters is how you parametrize the logUniform. If the...