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

Signals and communication technology

Exploring the Role of Tensor Networks in Designing Scalable Quantum Neural Networks

N. V. Krishna Rao, Panduraju Pagidimalla, Juluru Sai Rithwik, Konam Saiteja

Published Jan 1, 2026• 0 citations
Publisher
DOI
10.1007/978-981-95-1683-4_11

Related papers

Tensor Networks in Quantum Neural Network Architectures

K. Meenakshi, Rakhi Chauhan, Deepshikha Bhargava

Signals and communication technology•Jan 1, 2026•0 citations

Variational tensor neural networks for deep learning

Saeed S. Jahromi, Román Orús

Deep neural networks (NNs) encounter scalability limitations when confronted with a vast array of neurons, thereby constraining their achievable network depth. To address this challenge, we propose an integration of tensor networks (TN) into NN frameworks, combined with a variational DMRG-inspired training technique. This in turn, results in a scalable tensor neural network (TNN) architecture capable of efficient training over a large parameter space. Our variational algorithm utilizes a local gradient-descent technique, enabling manual or automatic computation of tensor gradients, facilitating design of hybrid TNN models with combined dense and tensor layers. Our training algorithm further provides insight on the entanglement structure of the tensorized trainable weights and correlation among the model parameters. We validate the accuracy and efficiency of our method by designing TNN models and providing benchmark results for linear and non-linear regressions, data classification and image recognition on MNIST handwritten digits.

arXiv:2211.14657•Scientific Reports•Aug 16, 2024•10 citations

Quantum-Classical Machine learning by Hybrid Tensor Networks

Ding Liu, Yao, Jiaqi, Z. Jamie Yao +1 more

Tensor networks (TN) have found a wide use in machine learning, and in particular, TN and deep learning bear striking similarities. In this work, we propose the quantum-classical hybrid tensor networks (HTN) which combine tensor networks with classical neural networks in a uniform deep learning framework to overcome the limitations of regular tensor networks in machine learning. We first analyze the limitations of regular tensor networks in the applications of machine learning involving the representation power and architecture scalability. We conclude that in fact the regular tensor networks are not competent to be the basic building blocks of deep learning. Then, we discuss the performance of HTN which overcome all the deficiency of regular tensor networks for machine learning. In this sense, we are able to train HTN in the deep learning way which is the standard combination of algorithms such as Back Propagation and Stochastic Gradient Descent. We finally provide two applicable cases to show the potential applications of HTN, including quantum states classification and quantum-classical autoencoder. These cases also demonstrate the great potentiality to design various HTN in deep learning way.

arXiv:2005.09428•May 15, 2020•7 citations

Tensor networks for quantum computing

A. V. Berezutskii, Minzhao Liu, Atithi Acharya +25 more

arXiv:2503.08626•Nature Reviews Physics•Jul 30, 2025•21 citations

Quantum Neural Network Architectures Based on Topological Qubits

Jincheng Zhang

This paper explores the design and implementation of quantum neural network (QNN) architectures leveraging the unique properties of topological qubits. Traditional QNNs face significant challenges regarding decoherence and scalability. Utilizing the inherent robustness of topological qubits – specifically their protection against local perturbations – presents a novel approach to constructing more reliable and efficient QNNs. We propose a framework for building QNNs based on topologically protected quantum bits, outlining the core mechanisms for information processing and demonstrating the potential for enhanced training stability. The architecture emphasizes the use of braiding operations to induce entanglement and the subsequent application of quantum algorithms for learning and inference. This work addresses a critical need for robust quantum computing platforms suitable for complex neural network training, moving beyond the limitations of current approaches. The presented architecture offers a pathway towards scalable and fault-tolerant QNNs, representing a significant step in realizing the full potential of quantum computation for artificial intelligence.

•Sep 5, 2026•0 citations

Quantum Neural Networks: From Concept to Simulation

Nasrullah Masud, Abdus Sobhan, Md Tanvir Islam Sourav +1 more

Information systems engineering and management•Jan 1, 2025•1 citation
Deep neural networks (NNs) encounter scalability limitations when confronted with a vast array of neurons, thereby constraining their achievable network depth. To address this challenge, we propose an integration of tensor networks (TN) into NN frameworks, combined with a variational DMRG-inspired training technique. This in turn, results in a scalable tensor neural network (TNN) architecture capable of efficient training over a large parameter space. Our variational algorithm utilizes a local gradient-descent technique, enabling manual or automatic computation of tensor gradients, facilitating design of hybrid TNN models with combined dense and tensor layers. Our training algorithm further provides insight on the entanglement structure of the tensorized trainable weights and correlation among the model parameters. We validate the accuracy and efficiency of our method by designing TNN models and providing benchmark results for linear and non-linear regressions, data classification and image recognition on MNIST handwritten digits.
Tensor networks (TN) have found a wide use in machine learning, and in particular, TN and deep learning bear striking similarities. In this work, we propose the quantum-classical hybrid tensor networks (HTN) which combine tensor networks with classical neural networks in a uniform deep learning framework to overcome the limitations of regular tensor networks in machine learning. We first analyze the limitations of regular tensor networks in the applications of machine learning involving the representation power and architecture scalability. We conclude that in fact the regular tensor networks are not competent to be the basic building blocks of deep learning. Then, we discuss the performance of HTN which overcome all the deficiency of regular tensor networks for machine learning. In this sense, we are able to train HTN in the deep learning way which is the standard combination of algorithms such as Back Propagation and Stochastic Gradient Descent. We finally provide two applicable cases to show the potential applications of HTN, including quantum states classification and quantum-classical autoencoder. These cases also demonstrate the great potentiality to design various HTN in deep learning way.
This paper explores the design and implementation of quantum neural network (QNN) architectures leveraging the unique properties of topological qubits. Traditional QNNs face significant challenges regarding decoherence and scalability. Utilizing the inherent robustness of topological qubits – specifically their protection against local perturbations – presents a novel approach to constructing more reliable and efficient QNNs. We propose a framework for building QNNs based on topologically protected quantum bits, outlining the core mechanisms for information processing and demonstrating the potential for enhanced training stability. The architecture emphasizes the use of braiding operations to induce entanglement and the subsequent application of quantum algorithms for learning and inference. This work addresses a critical need for robust quantum computing platforms suitable for complex neural network training, moving beyond the limitations of current approaches. The presented architecture offers a pathway towards scalable and fault-tolerant QNNs, representing a significant step in realizing the full potential of quantum computation for artificial intelligence.