Title
The Machine Learning Principles Based at the Quantum Mechanics Postulates
Date Issued
01 January 2022
Access level
metadata only access
Resource Type
conference paper
Publisher(s)
Springer Science and Business Media Deutschland GmbH
Abstract
Quantum mechanics is governed by well-defined postulates by the which one can go through either theory or experimental studies in order to perform measurements of microscopic dynamics of elementary particles, atoms and molecules for instance. By knowing the Tom Mitchell criteria inside Machine Learning, then one can wonder about the postulates of Quantum Mechanics in the entire picture of Mitchell criteria. This paper tries to answer this question. In essence it is focused on the role of brackets formalism and how it makes more feasible to project the ground principles of Quantum Mechanics in the arena of Machine Learning and Artificial Intelligence.
Start page
394
End page
403
Volume
506 LNNS
Language
English
OCDE Knowledge area
Ingeniería mecánica Termodinámica
Scopus EID
2-s2.0-85135010127
Source
Lecture Notes in Networks and Systems
ISSN of the container
23673370
ISBN of the container
9783031104602
Conference
Computing Conference, 2022 Virtual, Online
Sources of information: Directorio de Producción Científica Scopus