shared_randomstreams – Friendly random numbers¶
Since Theano uses a functional design, producing pseudo-random numbers in a graph is not quite as straightforward as it is in numpy.
The way to think about putting randomness into Theano’s computations is to put random variables in your graph. Theano will allocate a numpy RandomState object for each such variable, and draw from it as necessary. We will call this sort of sequence of random numbers a random stream.
For an example of how to use random numbers, see Using Random Numbers.
This is a symbolic stand-in for
numpy.random.RandomState. Random variables of various distributions are instantiated by calls to parent class
Returns: a list of all the (state, new_state) update pairs for the random variables created by this object
This can be a convenient shortcut to enumerating all the random variables in a large graph in the
updateparameter of function.
meta_seed will be used to seed a temporary random number generator, that will in turn generate seeds for all random variables created by this object (via gen).
gen(op, *args, **kwargs)¶
Return the random variable from op(*args, **kwargs), but also install special attributes (
RandomVariable) into it.
This function also adds the returned variable to an internal list so that it can be seeded later by a call to seed.
uniform, normal, binomial, multinomial, random_integers, ...
The shared variable whose
.valueis the numpy RandomState generator feeding this random variable.
A pair whose first element is a shared variable whose value is a numpy RandomState, and whose second element is an [symbolic] expression for the next value of that RandomState after drawing samples. Including this pair in the``updates`` list to function will cause the function to update the random number generator feeding this variable.