Loss Function

Creator
Creator
Seonglae Cho
Created
Created
2023 Mar 27 16:56
Editor
Edited
Edited
2025 Mar 24 16:32

Gradient Available

A function that quantifies the difference between predicted and actual outcomes.
Output type affects our choice of loss function
l:Y×YR+l: Y \times Y \rightarrow R_+
The loss of our network measures the cost incurred from incorrect predictions. L(f(x(i);W),y(i)),l(ϕ^(X),Y)L(f(x^{(i)};W), y^{(i)}), l(\hat{\phi}(X), Y)
decision-theoretic object that we are bringing in to quantify the negative consequences of error
 
 
 
 
 
 
 
 
 

Difference by Example

Loss Functions

Harmax
for interpretable AI
 
 

Recommendations