Small changes:
- the first chapter, we didn't specified -->> the first chapter, we didn't specify
- were looking for the validation loss -->> we're looking for the validation loss
Changing from
"as you might want your model to sometimes tell you it doesn't recognize any of the classes is has seen during training, and not pick a class because it has a slightly bigger activation score."
to
"as you might want your model to sometimes tell you it doesn't recognize any of the classes that it has seen during training, and not pick a class because it has a slightly bigger activation score."
Also, I think these phrases need a revision:
"Often, data scientists work with data with which they are not familiar as domain experts me"
"we first have to understand what the actual data and activations that are loss function is seen look like"
