Loss functions
Loss functions written below are provided as default by dannjs, see how to add more
These functions are represented below with yhat being the dannjs model predictions and y being the target values. The value n represents the length of the model's output array.
Binary Cross Entropy Loss. This function is common in machine learning especially for classification tasks.
Definition:
Mean Squared Error, this is one of the most commonly used loss functions in deep learning. This function determines a loss value by averaging the square of the difference between the predicted and desired output. It is also the default value for a Dannjs model.
Definition:
Mean Cubed Error, this is an experimental function. Cubing a number can output a negative value, this explains the |x|.
Definition:
Root Mean Squared Error, this function is the root of an mse output.
Definition:
Mean Absolute Error, this function determines the loss value by averaging the absolute difference between predicted and desired output.
Definition:
Mean Bias Error, this function determines a loss value by averaging the raw difference between the predicted and desired output. The output of this function can be negative, which makes this function less preferable than others.
Definition:
Log Cosh Loss, this function determines a loss value by averaging the of the difference between the predicted and desired output.
Definition:
Mean absolute exponential loss, this activaiton function is similar to mae but it offers a faster descent when approximately x = [-30.085,30.085] .
Definition:
Here is the graphed loss functions. The value x is the difference between y and yhat
