Let's say we have a support set, S, containing K examples as
. When given a query point (a new unseen example),
, the matching network predicts the class of
by comparing it with the support set.
We can define this as
is the parameterized neural network,
is the predicted class for the query point,
is the support set.
will return the probability of
belonging to each of the classes in the dataset. Then, we select the class of
as the one that has the highest probability. But how does this work exactly? How is this probability computed? Let's us see that now.
, for the query point,
, can be predicted as follows:
Let's decipher this equation.
are the input and labels of the support set.
is the query input— the input to which we want to predict the label....