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

Studies in computational intelligence

Advanced Stochastic Sequences for Multidimensional Integrals Used in Neural Networks

Venelin Todorov, Slavi G. Georgiev

Published Jan 1, 2024• 1 citation
Publisher
DOI
10.1007/978-3-031-57320-0_15

Related papers

Sequence Input-Based Quantum-Inspired Neural Networks with Applications

Panchi Li, Hong Yu Xiao

Neural Processing Letters•Aug 5, 2013•7 citations

Analytical derivatives of neural networks

Simone Rodini

arXiv:2105.02737•Computer Physics Communications•Sep 13, 2021•7 citations

Implementation of quantum stochastic walks for function approximation, two-dimensional data classification, and sequence classification

Lu-Ji Wang, Jia-Yi Lin, Shengjun Wu

We study a quantum stochastic neural network (QSNN) based on quantum stochastic walks on a graph, and use gradient descent to update the network parameters. We apply a toy model of QSNN with a few neurons to the problems of function approximation, two-dimensional data classification, and sequence classification. A simple QSNN with five neurons is trained to determine whether a sequence of words is a sentence or not, and we find that a QSNN can reduce the number of training steps. A QSNN with 11 neurons shows a quantum advantage in improving the accuracy of recognizing new types of inputs like verses. Moreover, with our toy model, we find the coherent QSNN is more robust against both label noise and device noise, compared with the decoherent QSNN. These results show that quantum stochastic walks may be a useful resource to implement a quantum neural network.

arXiv:2103.03018•Physical Review Research•Apr 20, 2022•10 citations

A New Optimized Stochastic Approach for Multidimensional Integrals in Machine Learning

Venelin Todorov, Stoyan Apostolov, Ivan Dimov +1 more

Stochastic techniques have been developed over many years in a range of different fields, but have only recently been applied to the problems in machine learning.A fundamental problem in this area is the accurate evaluation of multidimensional integrals.An introduction to the theory of the stochastic optimal generating vectors has been given.A new optimized lattice sequence with a special choice of the optimal generating vector has been applied to compute multidimensional integrals up to 30-dimensions.Clearly, the progress in the area of machine learning is closely related to the progress in reliable algorithms for multidimensional integration.

Annals of Computer Science and Information Systems•Sep 26, 2020•0 citations

Path Integrals for Stochastic Processes

Horacio S. Wio

WORLD SCIENTIFIC eBooks•Nov 15, 2012•71 citations

Effective many-body interactions in reduced-dimensionality spaces through neural network models

Senwei Liang, Karol Kowalski, Chao Yang +1 more

Accurately describing properties of challenging problems in physical sciences often requires complex mathematical models that are unmanageable to tackle head on. Therefore, developing reduced-dimensionality representations that encapsulate complex correlation effects in many-body systems is crucial to advance the understanding of these complicated problems. However, a numerical evaluation of these predictive models can still be associated with a significant computational overhead. To address this challenge, in this paper we discuss a combined framework that integrates recent advances in the development of active-space representations of coupled cluster (CC) downfolded Hamiltonians with neural network approaches. The primary objective of this effort is to train neural networks to eliminate the computationally expensive steps required for evaluating hundreds or thousands of Hugenholtz diagrams, which correspond to multidimensional tensor contractions necessary for evaluating a many-body form of downfolded effective Hamiltonians. Using small molecular systems (the H 2 O and HF molecules) as examples, we demonstrate that training neural networks employing effective Hamiltonians for a few nuclear geometries of molecules can accurately interpolate or extrapolate their forms to other geometrical configurations characterized by different intensities of correlation effects. We also discuss differences between effective interactions that define CC downfolded Hamiltonians with those of bare Hamiltonians defined by Coulomb interactions in the active spaces. Published by the American Physical Society 2024

arXiv:2407.05536•Physical Review Research•Dec 17, 2024•6 citations
We study a quantum stochastic neural network (QSNN) based on quantum stochastic walks on a graph, and use gradient descent to update the network parameters. We apply a toy model of QSNN with a few neurons to the problems of function approximation, two-dimensional data classification, and sequence classification. A simple QSNN with five neurons is trained to determine whether a sequence of words is a sentence or not, and we find that a QSNN can reduce the number of training steps. A QSNN with 11 neurons shows a quantum advantage in improving the accuracy of recognizing new types of inputs like verses. Moreover, with our toy model, we find the coherent QSNN is more robust against both label noise and device noise, compared with the decoherent QSNN. These results show that quantum stochastic walks may be a useful resource to implement a quantum neural network.
Stochastic techniques have been developed over many years in a range of different fields, but have only recently been applied to the problems in machine learning.A fundamental problem in this area is the accurate evaluation of multidimensional integrals.An introduction to the theory of the stochastic optimal generating vectors has been given.A new optimized lattice sequence with a special choice of the optimal generating vector has been applied to compute multidimensional integrals up to 30-dimensions.Clearly, the progress in the area of machine learning is closely related to the progress in reliable algorithms for multidimensional integration.
Accurately describing properties of challenging problems in physical sciences often requires complex mathematical models that are unmanageable to tackle head on. Therefore, developing reduced-dimensionality representations that encapsulate complex correlation effects in many-body systems is crucial to advance the understanding of these complicated problems. However, a numerical evaluation of these predictive models can still be associated with a significant computational overhead. To address this challenge, in this paper we discuss a combined framework that integrates recent advances in the development of active-space representations of coupled cluster (CC) downfolded Hamiltonians with neural network approaches. The primary objective of this effort is to train neural networks to eliminate the computationally expensive steps required for evaluating hundreds or thousands of Hugenholtz diagrams, which correspond to multidimensional tensor contractions necessary for evaluating a many-body form of downfolded effective Hamiltonians. Using small molecular systems (the H 2 O and HF molecules) as examples, we demonstrate that training neural networks employing effective Hamiltonians for a few nuclear geometries of molecules can accurately interpolate or extrapolate their forms to other geometrical configurations characterized by different intensities of correlation effects. We also discuss differences between effective interactions that define CC downfolded Hamiltonians with those of bare Hamiltonians defined by Coulomb interactions in the active spaces. Published by the American Physical Society 2024