Abstract
For Machine Learning (ML) classification problem, where a vector of --observations (values of attributes) is mapped to a single value (class label), a generalized Radon--Nikodym type of solution is proposed. Quantum--mechanics --like probability states are considered and "Cluster Centers", corresponding to the extremums of , are found from generalized eigenvalues problem. The eigenvalues give possible outcomes and corresponding to them eigenvectors define "Cluster Centers". The projection of a state, localized at given to classify, on these eigenvectors define the probability of outcome, thus avoiding using a norm ( or other types), required for "quality criteria" in a typical Machine Learning technique. A coverage of each `Cluster Center" is calculated, what potentially allows to separate system properties (described by outcomes) and system testing conditions (described by coverage). As an example of such application distribution estimator is proposed in a form of pairs , that can be considered as Gauss quadratures generalization. This estimator allows to perform probability distribution estimation in a strongly non--Gaussian case.
Connections
Explore this paper’s authors, topics and related work.
Building this map preview
BZPEER is loading the nearby papers, people, topics and institutions for this page.
Reviews 0
Write a review
No reviews yet.
Discussion 0
Add a comment
No comments yet.