Loss FunctionLoss Function | Usually for a single training sample Given a model output and a true value y, the loss function is |
Cost FunctionCost Function | Usually the total loss over the entire training set (or a mini-batch when using mini-batch gradient descent) |
Objective Function | Represents any function that wishes to be optimized The cost function is a type of objective function |
Machine learning notes: Concept comparison - loss function, cost function, objective function
Guess you like
Origin blog.csdn.net/qq_40206371/article/details/133187920
Recommended
Ranking