February 2019
Intermediate to advanced
260 pages
6h 3m
English
Choosing the triplets is very important as it impacts the learning of the network.
For negative cases, we just choose them randomly, and most of the time, they actually satisfy the equation easily. The reason for this is, the difference between the anchor and negative image is already great. Thus, no matter the value that you choose, the difference will always be large. We can express this mathematically as the following:
![]()
The network at this point will get lazy and not solve the equations for the upcoming iterations. To resolve this, we need to choose triplets that are complex to train:
This means that we need to choose ...
Read now
Unlock full access