Glossario IA
Il dizionario completo dell'Intelligenza Artificiale
Contrastive Loss
Learning objective that pulls similar pairs together and pushes dissimilar pairs apart in the embedding space.
Distance Metric Learning
Machine learning paradigm that aims to optimize a distance function to better separate classes or cluster similarities.
Similarity Function
Mathematical function that quantifies the degree of resemblance between two objects in a given representation space.
Metric Space
Mathematical space equipped with a distance function that satisfies the axioms of non-negativity, symmetry, and the triangle inequality.
K-Nearest Neighbors (KNN)
Classification algorithm based on the distance of the K nearest neighbors in the meta-learned embedding space.
Euclidean Distance
Standard geometric distance in a Euclidean space, calculated as the square root of the sum of the squared differences.
Manhattan Distance
Distance calculated as the sum of the absolute values of the differences between the coordinates of two points.