Hands-On Meta Learning with Python

Adversarial meta learning

Now, we define a class called ADML where we implement the ADML algorithm. In the __init__ method, we will initialize all of the necessary variables. Then, we define our sigmoid function and we define our train function.

We will see this step-by-step and later see the final code as a whole:

class ADML(object):

We define the __init__ method and initialize necessary variables:

    def __init__(self):

We initialize a number of tasks—that is, the number of tasks we need in each batch of tasks:

        self.num_tasks = 2

We initialize a number of samples—that is, a number of shots—a number of data points (k) we need to have in each task:

        self.num_samples = 10

We initialize a number of epochs—that is, training iterations:

 self.epochs ...