Pontificia Universidad Católica de Chile Pontificia Universidad Católica de Chile
Torres-Torriti, M., Calderara Cea, F. (2023). Statistical Machine Learning. In: Zhang, Q. (eds) Encyclopedia of Smart Agriculture Technologies. Springer, Cham. https://doi.org/10.1007/978-3-030-89123-7_227-1 (2023)

Simultaneous localization and mapping (SLAM) or concurrent mapping and localization (CML) is a computational process by which a robot creates a map of an environment not known in advance, while at the same localizing itself in the environment. SLAM algori

Revista : Encyclopedia of Smart Agriculture Technologies. Springer, 2023 Springer Nature Switzerland AG
Páginas : 1-32
Tipo de publicación : Publicaciones No WOS Ir a publicación


Statistical machine learning is the field concerned with the development of computational approaches by which a computer can learn from data without using a set of different handcrafted rules or heuristics (Bishop 2006). Thus, statistical machine learning algorithms build mathematical prediction models from data using statistical and optimization techniques to find the best model that minimizes the prediction error measured in terms of an expected loss measure. The most popular algorithms for statistical machine learning include nearest neighbor methods, Bayesian learning (including maximum a posteriori and maximum likelihood estimation and the naïve Bayes classifier), support vector machines, decision trees, and neural networks to find patterns in data and make predictions. The goal of statistical machine learning is to create models that generalize well and that can learn and improve over time, becoming more accurate as they are exposed to more data. A machine learning algorithm that generalizes well is one that builds a model capable of predicting or classifying correctly new data that has not been observed before.