Question: Given a general classification problem (e.g., identifying cats, dogs and people from images), is it better to use a one-hot representation with a loss such
Given a general classification problem (e.g., identifying cats, dogs and people from images), is it better to use a one-hot representation with a loss such as cross-entropy (CE) than to treat the problem as a regression problem with a loss such as mean-squared-error (MSE)
Step by Step Solution
There are 3 Steps involved in it
Get step-by-step solutions from verified subject matter experts
