Kelp.Net is comprised of a single abstract LossFunction class, designed to be implemented for your specific instance in determining how you evaluate loss.
In machine learning, a loss function or cost function is a function that maps an event or values of one or more variables onto a real number intuitively, representing some cost associated with the event. Kelp.Net offers two out-of-the-box loss functions: mean squared error and softmax cross entropy. You can easily extend these to meet your needs.