A representation of an object as a list of numbers.
Hyperparameters specify the model's architecture and how it will be trained and are not learned during training phase.
A function that helps to separate datasets that can't be separated with a classic linear approach.
Lipschitzness is a noun coming from the term Lipschitz continuity.
Function that is used to evaluate the performance of a model and guide the training process.
An algorithm that removes less important data from a dataset.
Internal variables of the model that will be updated during the training phase (e.g. weights and biases of a neural network).
A simple function of x returning 0 if x < 0 or x otherwise.
A multidimensional array similar to numpy.array.