Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

Lecture notes in computer science

A Quantization-Model of the Neural Nets

Matthias Reuter

Published Jan 1, 1999• 4 citations
Publisher
DOI
10.1007/3-540-48774-3_58

Related papers

Quantum Neural Nets

Michail A. Zak, Colin P. Williams

International Journal of Theoretical Physics•Feb 1, 1998•60 citations

To the mathematical theory of representation of information in neural nets

A. F. Zaritskii

Ukrainian Mathematical Journal•Dec 1, 1995•1 citation

Quantum neuronal nets-a new tool in neural network modelling

Maciej Lewenstein, Mariusz A. Olko

Acta Neurobiologiae Experimentalis•Jan 1, 1992•0 citations

Quantum neural network application for exudate affected retinal image patch identification

Ankit Sarkar, Minakshi Banerjee, Mahua Nandy Pal

In the field of retinal disease identification, deep neural networks are exhaustively used. But the efficiency of quantum neural network in the field is not yet explored. Recently, quantum neural network achieved attention of researchers as it is required to explore if quantum network has any scope in the relevant field in terms of resource utilisation and decision-making during network learning. In this paper, efficiency of a simple quantum network model is experimented. In the present scenario, quantum classical models are unable to handle more than few qubits. Experimentally, it is found that the quantum neural network is quite efficient in representing the features of exudate affected retinal image patches. The accuracy of quantum neural net model is 84.28%. The accuracies are 51.80% and 88% respectively with comparable deep neural net and convolutional neural net models.

International Journal of Computational Vision and Robotics•Jan 1, 2021•0 citations

Quantization in Neural Networks

Alexander J. Weissblut

Communications in computer and information science•Jan 1, 2022•3 citations

A spatial quantum neural computer

Elizabeth Behrman, James E. Steck, S.R. Skinner

We take another step towards the construction of a bench model of quantum neural network hardware: the simulation of a spatial array of quantum dot molecules, acting as a neural network. Like our previous temporal model (1998), this net has none of the "wiring problems" of hardware for traditional neural nets: the necessary connections are supplied by the physical system itself. Computation is performed by the intrinsic physics of the system. The long range character of the phononic interactions takes the net beyond traditional nearest neighbor connectionist systems. Moreover, unlike our temporal model, there would seem to be few inherent problems to the hardware implementation of this architecture.

International Joint Conference on Neural Networks (IJCNN)•Jan 22, 2003•19 citations
In the field of retinal disease identification, deep neural networks are exhaustively used. But the efficiency of quantum neural network in the field is not yet explored. Recently, quantum neural network achieved attention of researchers as it is required to explore if quantum network has any scope in the relevant field in terms of resource utilisation and decision-making during network learning. In this paper, efficiency of a simple quantum network model is experimented. In the present scenario, quantum classical models are unable to handle more than few qubits. Experimentally, it is found that the quantum neural network is quite efficient in representing the features of exudate affected retinal image patches. The accuracy of quantum neural net model is 84.28%. The accuracies are 51.80% and 88% respectively with comparable deep neural net and convolutional neural net models.
We take another step towards the construction of a bench model of quantum neural network hardware: the simulation of a spatial array of quantum dot molecules, acting as a neural network. Like our previous temporal model (1998), this net has none of the "wiring problems" of hardware for traditional neural nets: the necessary connections are supplied by the physical system itself. Computation is performed by the intrinsic physics of the system. The long range character of the phononic interactions takes the net beyond traditional nearest neighbor connectionist systems. Moreover, unlike our temporal model, there would seem to be few inherent problems to the hardware implementation of this architecture.