What It Does
One-Shot learning can be useful when you want to identify someone just by giving the predicting model a single picture of them.
Similarity Function
A model can perform One-shot learning by learning a “similarity” function. When the model receives an input, the model calculates the degree of difference between the input and all the people who are in the database. If the calculated difference is below a specified threshold, the two pairs would be stated to be “similar”. After the model looks through all the people in the database, the model would output the person who has the smallest difference score.
