A root word is a word with no prefixes or suffixes, meaning that it is the primary lexical unit of a set of words and represents the principle semantic meaning of the set.
Lemmatization is the process of reducing a word to its lemma (canonical form). In natural language processing, a lemmatizer may be used to reduce all words in a given text to their lemmas, which makes comparative analysis possible based on canonical forms.
A feedforward neural network (aka multilayer perceptron or deep feedforward network) is a supervised learning network in which information only flows forward.
Loss functions are used to quantify to what extent a prediction was right/wrong (rather than simply if it was right or wrong.) The purpose of a loss function is to work as part of the optimization process to update a neural network so that it reaches the desired result.
Overfitting is a phenomenon in statistics and machine learning, wherein a model maximizes performance on training data to the extent that it is unsuitable for unseen data.