Quantum Neural Networks and Topological Quantum Field Theories

Autor:	Antonino Marcianò, Deen Chen, Filippo Fabrocini, Chris Fields, Enrico Greco, Niels Gresnigt, Krid Jinklub, Matteo Lulli, Kostas Terzidis, Emanuele Zappala
Přispěvatelé:	Marcianò, Antonino, Chen, Deen, Fabrocini, Filippo, Fields, Chri, Greco, Enrico, Gresnigt, Niel, Jinklub, Krid, Lulli, Matteo, Terzidis, Kosta, Zappala, Emanuele
Jazyk:	angličtina
Rok vydání:	2022
Předmět:	Machine Learning Topological quantum field theory Topological quantum neural networks Artificial Intelligence Quantum perceptron Cognitive Neuroscience Quantum Theory Quantum amplitude classifiers Neural Networks Computer Graph neural networks Graph neural network Quantum amplitude classifier
Popis:	Our work intends to show that: (1) Quantum Neural Networks (QNNs) can be mapped onto spin-networks, with the consequence that the level of analysis of their operation can be carried out on the side of Topological Quantum Field Theory (TQFT); (2) A number of Machine Learning (ML) key-concepts can be rephrased by using the terminology of TQFT. Our framework provides as well a working hypothesis for understanding the generalization behavior of DNNs, relating it to the topological features of the graph structures involved. (c) 2022 Elsevier Ltd. All rights reserved.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_dedup___::c3edea092b08760c80d872e3a8ce4152 https://www.sciencedirect.com/science/article/abs/pii/S0893608022002027 Zobrazit plný text záznamu