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.

• machine learning
• reference
• statistics

An activation function is used to determine whether an input in a feedforward neural network is moved from one layer to the next.

• deep learning
• neural networks
• reference

A lemma is the canonical form of a word, also known as the dictionary form because it is often used as the primary entry in a dictionary.

• linguistics
• nlp
• reference

Decreasing coupling with the principle of least knowledge.

• design
• principles
• reference
• software

Guidelines for the effective partitioning of a software product's codebase.

• principles
• reference
• software

The relationship between 'injecting' and 'inverting' dependencies in object-oriented design.

• design
• principles
• reference
• software