Objective Function = Loss Function + Regularization Penalty/Term
L1 loss = least absolute error = Sum(| y - f(x) |)
L2 loss = least square error = Sum((y - f(x))^2)
regularization term in order to prevent the coefficients to fit so perfectly to overfit.
L1 reg = the sum of the weights.
L2 reg = the sum of the square of the weights
L1 loss = least absolute error = Sum(| y - f(x) |)
L2 loss = least square error = Sum((y - f(x))^2)
regularization term in order to prevent the coefficients to fit so perfectly to overfit.
L1 reg = the sum of the weights.
L2 reg = the sum of the square of the weights
No comments:
Post a Comment