- class LearningRate(learning_rate)#
Represents a Learning Rate. Will be an attribute of
GradientDescentState. Note that
GradientDescentalso has a learning rate. That learning rate can be a float, a list, an array, a function returning a generator and will be used to create a generator to be used during the optimization process. This class wraps
Generatorso that we can also access the last yielded value.
Returns the current value of the learning rate.
Raise GeneratorExit inside generator.
Send a value into the generator. Return next yielded value or raise StopIteration.
- throw(typ, val=None, tb=None)#
Raise an exception in the generator. Return next yielded value or raise StopIteration.