tensornn.loss

This file contains the loss functions used in TensorNN. Loss functions are ways your neural network calculates how off its calculations are. Then this information is used to improve/train it.

Classes

BinaryCrossEntropy	Sigmoid is the only activation function compatible with BinaryCrossEntropy loss.
CategoricalCrossEntropy	It is recommended to use the Softmax activation function with this loss.
Loss	Base loss class.
MAE	Mean absolute error is MSE but instead of squaring the values, you absolute value them.
MSE	Mean squared error is calculated extremely simply.
MSLE	Mean squared logarithmic error is MSE but taking the log of our values before subtraction.
Poisson	Poisson loss is calculated with this formula: average of (pred-desired*logₑ(pred))
RMSE	Root mean squared error is just MSE, but it includes a square root after taking the average.
RSS	Residual sum of squares loss is MSE but instead of doing the mean, you do the sum.
SquaredHinge	Square hinge loss is calculated with this formula: max(0, 1-pred*desired)^2