Hi,
My question 7 indicates the following:
“Neural style transfer uses images Content C, Style S. The loss function used to generate image G is composed of which of the following: (Choose all that apply.)”
However, the slides related to Neural style transfer mention only the cost function.
When used in this generic way, “loss” and “cost” are equivalent terms.
If you want to be fully precise, usually Prof Ng will reserve the term “loss function” for a vector valued function with one output per sample or in some more detailed cases like image segmentation perhaps one value per pixel per sample. Whereas “cost function” usually refers to a scalar valued function which is the average of the “loss” values.
Thanks for answering; it was helpful!
