Superpositional Quantum Network Topologies |
| |
Authors: | Christopher?Altman Jaroslaw?Pykacz Email author" target="_blank">Romàn?R?ZapatrinEmail author |
| |
Institution: | (1) Quantum Information Science and Technology Project, ATIP, Tokyo, Japan;(2) Universiteit van Amsterdam, The Netherlands;(3) Instytut Matematyki, Uniwersytet Gdaski, Wita Stwosza, Gdask, Poland;(4) Center Leo Apostel of the Vrije Universiteit Brussels (VUB), Krijgskundestraat, Brussel;(5) Friedmann Lab. for Theoretical Physics, SPb UEF, Griboyedova, St. Petersburg, Russia |
| |
Abstract: | We introduce superposition-based quantum networks composed of (i) the classical perceptron model of multilayered, feedforward neural networks and (ii) the algebraic model of evolving reticular quantum structures as described in quantum gravity. The main feature of this model is moving from particular neural topologies to a quantum metastructure which embodies many differing topological patterns. Using quantum parallelism, training is possible on superpositions of different network topologies. As a result, not only classical transition functions, but also topology becomes a subject of training. The main feature of our model is that particular neural networks, with different topologies, are quantum states. We consider high-dimensionaldissipative quantum structures as candidates for implementation of the model. |
| |
Keywords: | Neural networks quantum topology |
本文献已被 SpringerLink 等数据库收录! |
|