pith. sign in

arxiv: 2605.30724 · v1 · pith:A2UXTUQEnew · submitted 2026-05-29 · 🪐 quant-ph

Research progress on quantum neural networks and quantum machine learning

Yifan Sun , Boyuan Sun , Jiameng Tian , Xiangdong Zhang This is my paper

Pith reviewed 2026-06-28 22:24 UTC · model grok-4.3

classification 🪐 quant-ph
keywords quantum neural networksquantum machine learningQNN architecturesperformance metricsquantum convolutional networksquantum reservoir computingquantum reinforcement learning
0
0 comments X

The pith

A survey reviews quantum neural network architectures and summarizes their performance in accuracy, training time, and resources.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

This paper surveys quantum neural networks as an approach that applies quantum mechanics to machine learning tasks such as data analysis and pattern recognition. It examines fully connected QNNs, quantum convolutional neural networks, equivariant QNNs, quantum Hopfield networks, quantum Boltzmann machines, quantum reservoir computing, and composite networks used for reinforcement learning, generative learning, and transfer learning. The authors collect reported results on learning accuracy, training time, and resource requirements for each type. A sympathetic reader would care because the review shows that each architecture has its own strengths and weaknesses for different applications.

Core claim

The survey examines various QNN approaches, including fully connected QNNs, quantum convolutional neural networks, equivariant QNNs, quantum Hopfield networks, quantum Boltzmann machines, quantum reservoir computing, and composite networks for quantum reinforcement learning, quantum generative learning, and quantum transfer learning. We summarize the relevant investigations on their performance, including learning accuracy, training time, and resource requirements, etc. Each QNN type has unique strengths and weaknesses, offering diverse solutions for different applications.

What carries the argument

The taxonomy of QNN types (fully connected, convolutional, equivariant, Hopfield, Boltzmann, reservoir, and composite) and the collection of their performance metrics across applications.

If this is right

  • Each QNN type offers unique strengths and weaknesses suited to different machine learning applications.
  • Performance in learning accuracy, training time, and resource requirements varies by architecture.
  • Composite networks support quantum reinforcement learning, generative learning, and transfer learning.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • Practitioners could match QNN type to task requirements to balance accuracy against hardware costs.
  • Standardized reporting of metrics across studies would strengthen future comparisons of these architectures.
  • The review implies that quantum effects in these networks may help address growing data volumes in classical machine learning.

Load-bearing premise

The reviewed studies provide comparable performance metrics that can be meaningfully summarized across different QNN architectures and applications without major inconsistencies in experimental setups or reporting standards.

What would settle it

Discovery that many reviewed studies use incompatible experimental setups or report metrics in non-comparable ways would prevent reliable cross-architecture summarization.

Figures

Figures reproduced from arXiv: 2605.30724 by Boyuan Sun, Jiameng Tian, Xiangdong Zhang, Yifan Sun.

Figure 1
Figure 1. Figure 1: Timeline highlighting major advancements several basic structures of QNNs and quantum machine learning. Those ones highly relevant to this review are marked out by colored background. reinforcement learning, generative learning, transfer learning, or unsupervised learning). Consequently, one must tune the parameters of a QNN so that the deviation (or bias) of the model output from the target output is mini… view at source ↗
Figure 2
Figure 2. Figure 2: (a) A sketch of a Classical NN, with input data vector 𝑥. (b) The FCQNN, with input data carried by quantum state |𝑥⟩. (c) The QCNNs. 𝜌𝑖𝑛 denotes the density matrix of the input. (d) The QDNNs. (e) The QBMs. Several qubits are used as the hidden ones, and others are used as the visible ones. (f) The QRCs. The blue blocks, orange blocks, and the green blocks represent single qubit gates, two-qubit gates, an… view at source ↗
Figure 3
Figure 3. Figure 3: The learning process of a QNN vs a classical NN, in a generalized perspective of data flow. By using a QNN (the left panel), the data is encoded by quantum states (in the subspace 1 ), and transformed to other states (in the subspace 2 ). The training is done by computing the loss function of the output states, and updating the parameters of the QNN. By using a classical NN (the right panel), the data is… view at source ↗
Figure 4
Figure 4. Figure 4: A graphic illustration of the core requirements of QRL, QGL, and QTL. The roles of the basic types of the QNN for those learning paradigms are also illustrated, as indicated by blue arrows. The quantum operations on states, such as applying quantum algorithms or performing measurements, can be employed as a quantum version of alignment and reward feedback, as indicated by red arrows. combine into more comp… view at source ↗
Figure 5
Figure 5. Figure 5: Schematic of a QTL framework. A QNN-based agent interacts with an environment by observing a state 𝑠𝑡 , selecting an action 𝑎𝑡 according to its policy, and receiving a reward 𝑟𝑡 as the environment transitions to a new state 𝑠𝑡+1 with probability 𝑝(𝑠𝑡+1|𝑠𝑡 , 𝑎𝑡 ). After collecting a set of transitions (𝑠𝑡 , 𝑎𝑡 , 𝑟𝑡 , 𝑠𝑡+1), the agent is updated using a suitable optimization algorithm. Moreover, Grover-like … view at source ↗
Figure 6
Figure 6. Figure 6: A schematic of QGANs. The generator and discriminator are QNNs. The adversarial training of them finally reaches the point that the data output by the generator cannot be picked out from the real data by the discriminator. is transferable and how to adapt it effectively. This assessment is performed by an alignment subroutine, which measures the similarity between the source and target distributions and id… view at source ↗
Figure 7
Figure 7. Figure 7: A schematic of QNNs for transfer learning. The information learned from the source data are aligned to the learning process of target data. 5. QNNs with Other Structures Beyond the previously discussed families of QNNs, several other architectures incorporate specific structural innovations that enhance their expressivity, trainability, or applicability to particular tasks. Although these structures have r… view at source ↗
Figure 8
Figure 8. Figure 8: An illustration of using decomposition as a network. The whole structure could be reformed as a layerwised structure under special constrains. vectorized nonlinear activation function that acts elementwise on each component of a vector (possibly with different particular form per component). Then, a nonlinear PBNN can be defined as 𝑓̃(𝐱; 𝜽̃) = 𝜎 [ 𝑾 𝐾 ( 𝒑𝐾, 𝜎 [ 𝑾 𝐾−1 ( 𝒑𝐾−1, ⋯ 𝜎 [ 𝑾 2 ( 𝒑2 , 𝜎 [ 𝑾 1 ( 𝒑1 ,… view at source ↗
read the original abstract

Machine learning holds fundamental computational significance due to the increasing demand for efficient solutions to complex tasks in data analysis, pattern recognition, and optimization, which are essential for addressing the multifaceted challenges of modern society. As the volume of data proliferates at an unprecedented rate, the need for more powerful machine learning strategies becomes increasingly evident. Quantum neural networks (QNNs) represent an emerging and transformative research field that seeks to harness the unique principles of quantum mechanics to enhance the capabilities of machine learning algorithms. This survey examines various QNN approaches, including fully connected QNNs, quantum convolutional neural networks, equivariant QNNs, quantum Hopfield networks, quantum Boltzmann machines, quantum reservoir computing, and composite networks for quantum reinforcement learning, quantum generative learning, and quantum transfer learning. We summarize the relevant investigations on their performance, including learning accuracy, training time, and resource requirements, etc. Each QNN type has unique strengths and weaknesses, offering diverse solutions for different applications.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

2 major / 1 minor

Summary. This manuscript is a survey reviewing quantum neural networks (QNNs) and quantum machine learning. It covers fully connected QNNs, quantum convolutional neural networks, equivariant QNNs, quantum Hopfield networks, quantum Boltzmann machines, quantum reservoir computing, and composite networks applied to quantum reinforcement learning, generative learning, and transfer learning. The central contribution is a summary of performance investigations across these architectures, including learning accuracy, training time, and resource requirements, along with notes on each type's unique strengths and weaknesses.

Significance. If the performance summaries can be reliably aggregated and compared, the survey could serve as a useful organizing reference for the quantum machine learning community. The work has no formal derivations or machine-checked proofs, and its value rests entirely on the quality and consistency of the literature compilation.

major comments (2)
  1. [Abstract] Abstract: The claim that the survey 'summarizes the relevant investigations on their performance, including learning accuracy, training time, and resource requirements' presupposes that metrics from the cited studies are sufficiently standardized for cross-architecture and cross-application comparison; the manuscript provides no discussion of experimental-setup heterogeneity, normalization procedures, or reporting biases that would support this aggregation.
  2. [Abstract] Abstract: No selection criteria, search strategy, or inclusion/exclusion rules for the reviewed literature are stated, making it impossible to assess whether the summarized performance claims are representative or subject to selection bias.
minor comments (1)
  1. [Abstract] The abstract lists seven QNN categories but does not indicate the approximate number of papers reviewed per category or the time period covered.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the constructive comments. We agree that the abstract and manuscript would benefit from greater transparency regarding literature selection and the limitations of cross-study performance comparisons. We will revise accordingly.

read point-by-point responses

  1. Referee: [Abstract] Abstract: The claim that the survey 'summarizes the relevant investigations on their performance, including learning accuracy, training time, and resource requirements' presupposes that metrics from the cited studies are sufficiently standardized for cross-architecture and cross-application comparison; the manuscript provides no discussion of experimental-setup heterogeneity, normalization procedures, or reporting biases that would support this aggregation.

    Authors: We acknowledge that the manuscript does not discuss heterogeneity of experimental setups, normalization, or reporting biases. In the revised version we will add a short subsection (likely in the introduction or a new 'Limitations of Cross-Study Comparison' paragraph) that explicitly notes these issues and qualifies the performance summaries as illustrative rather than directly comparable. The abstract will also be rephrased to avoid implying standardized aggregation. revision: yes

  2. Referee: [Abstract] Abstract: No selection criteria, search strategy, or inclusion/exclusion rules for the reviewed literature are stated, making it impossible to assess whether the summarized performance claims are representative or subject to selection bias.

    Authors: The current manuscript does not state selection criteria or search strategy. We will add a concise 'Literature Selection' paragraph (or subsection) describing the approach used (e.g., keyword searches on arXiv and major journals, focus on papers reporting quantitative performance metrics for the listed architectures, and time window). The abstract will be updated to reference this methodology. This addresses the concern about potential selection bias. revision: yes

Circularity Check

0 steps flagged

No circularity: survey compiles external literature without derivations or self-referential predictions

full rationale

The paper is explicitly a survey reviewing QNN variants (fully connected, QCNN, equivariant, Hopfield, Boltzmann, reservoir, composite) and summarizing reported metrics from prior studies. No original equations, derivations, fitted parameters, or predictions appear in the abstract or described structure. All load-bearing content consists of citations to independent external work; no self-citation chains, ansatzes, or renamings reduce claims to the paper's own inputs. The noted assumption about cross-study metric comparability is an external-validity issue, not an internal circular reduction. Score 0 is the appropriate finding for a self-contained review.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

This is a survey paper; no free parameters, axioms, or invented entities are introduced by the authors.

pith-pipeline@v0.9.1-grok · 5697 in / 1030 out tokens · 25035 ms · 2026-06-28T22:24:13.033450+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

276 extracted references · 40 canonical work pages · 10 internal anchors

  1. [1]

    Kussul, T

    E. Kussul, T. Baidyk, D. C. Wunsch, Classical neural networks, in: Neural Networks and Micromechanics. Springer, Berlin, Heidelberg, 2010

    2010

  2. [2]

    LeCun, Y

    Y. LeCun, Y. Bengio, G. Hinton, Deep learning, Nature 521 (2015) 436–444

    2015

  3. [3]

    Biamonte, P

    J. Biamonte, P. Wittek, N. Pancotti, P. Rebentrost, N. Wiebe, S. Lloyd, Quantum machine learning, Nature 549 (2017) 195–202

    2017

  4. [4]

    Beer, et al., Training deep quantum neural networks, Nat

    K. Beer, et al., Training deep quantum neural networks, Nat. Commun. 11 (2020) 808

    2020

  5. [5]

    Kak, Quantum neural computing, in: P

    S. Kak, Quantum neural computing, in: P. W. Hawkes (Ed.), Advances in Imaging and Electron Physics, volume 94, Elsevier, 1995, pp. 259–313

    1995

  6. [6]

    Menneer, A

    T. Menneer, A. Narayanan, Quantum-inspired neural networks, Technical Report R329, CiteSeerX, 1995

    1995

  7. [7]

    Y. Ma, C. Gong, Hopfield spin-glass model in a transverse field, Phys. Rev. B 48 (1993) 12778

    1993

  8. [8]

    Y.Ma,C.Gong, StatisticalmechanicsofamulticonnectedHopfieldneural-networkmodelinatransversefield, Phys.Rev.E51(1995)1573

    1995

  9. [9]

    Ventura, T

    D. Ventura, T. Martinez, A quantum associative memory based on grover’s algorithm, in: Artificial Neural Nets and Genetic Algorithms, Springer, 1999, pp. 22–27

    1999

  10. [10]

    Peruš, Neural networks as a basis for quantum associative networks, Neural Netw

    M. Peruš, Neural networks as a basis for quantum associative networks, Neural Netw. World 10 (2000) 1001–1013

    2000

  11. [11]

    Ventura, Implementing competitive learning in a quantum system, in: Proceedings of the 1999 International Joint Conference on Neural Networks (IJCNN’99), volume 1, IEEE, 1999, pp

    D. Ventura, Implementing competitive learning in a quantum system, in: Proceedings of the 1999 International Joint Conference on Neural Networks (IJCNN’99), volume 1, IEEE, 1999, pp. 462–466

    1999

  12. [12]

    (III Fundam

    N.Matsui,M.Takai,H.Nishimura, Anetworkmodelbasedonqubitlikeneuroncorrespondingtoquantumcircuit, Electron.Commun.Jpn. (III Fundam. Electron. Sci.) 83 (2000) 67–73

    2000

  13. [13]

    Kouda, N

    N. Kouda, N. Matsui, H. Nishimura, F. Peper, Qubit neural network and its learning efficiency, Neural Comput. Appl. 14 (2005) 114–121

    2005

  14. [14]

    Quantum neural network

    M. Altaisky, Quantum neural network, arXiv quant-ph/0107012 (2001). Y. Sun, et al:Preprint submitted to ElsevierPage 40 of 47 Research progress on QNNs and QML

    work page internal anchor Pith review Pith/arXiv arXiv 2001

  15. [15]

    R. Zhou, Q. Ding, Quantum m-p neural network, Int. J. Theor. Phys. 46 (2007) 3209–3215

    2007

  16. [16]

    Quantum Deep Learning

    N. Wiebe, A. Kapoor, K. M. Svore, Quantum deep learning, arXiv 1412.3489 (2014)

    work page internal anchor Pith review Pith/arXiv arXiv 2014

  17. [17]

    Fujii, K

    K. Fujii, K. Nakajima, Harnessing disordered-ensemble quantum dynamics for machine learning, Phys. Rev. Appl. 8 (2017) 024030

    2017

  18. [18]

    I. Cong, S. Choi, M. D. Lukin, Quantum convolutional neural networks, Nat. Phys. 15 (2019) 1273–1278

    2019

  19. [19]

    Skolik, M

    A. Skolik, M. Cattelan, S. Yarkoni, T. Bäck, V. Dunjko, Equivariant quantum circuits for learning on weighted graphs, npj Quantum Inf. 9 (2023) 47

    2023

  20. [20]

    M. T. West, M. Sevior, M. Usman, Reflection equivariant quantum neural networks for enhanced image classification, Mach. Learn.: Sci. Technol. 4 (2023) 035027

    2023

  21. [21]

    Bödeker, E

    L. Bödeker, E. Fiorelli, M. Müller, Optimal storage capacity of quantum Hopfield neural networks, Phys. Rev. Res. 5 (2023) 023074

    2023

  22. [22]

    Lewis, D

    L. Lewis, D. Gilboa, J. R. McClean, Quantum advantage for learning shallow neural networks with natural data distributions, arXiv 2503.20879 (2025)

    work page arXiv 2025

  23. [23]

    H. J. Briegel, G. De las Cuevas, Projective simulation for artificial intelligence, Sci. Rep. 2 (2012) 1

    2012

  24. [24]

    Crawford, A

    D. Crawford, A. Levit, N. Ghadermarzy, J. S. Oberoi, P. Ronagh, Reinforcement learning using quantum Boltzmann machines, Quantum Inf. Comput. 18 (2018) 51

    2018

  25. [25]

    Lloyd, C

    S. Lloyd, C. Weedbrook, Quantum adversarial generative learning, Phys. Rev. Lett. 121 (2018) 040502

    2018

  26. [26]

    Gokhale, M

    A. Gokhale, M. B. Pande, D. Pramod, Implementation of a quantum transfer learning approach to image splicing detection, Int. J. Quantum Inf. 18 (2020) 2050024

    2020

  27. [27]

    L. Wang, Y. Sun, X. Zhang, Quantum deep transfer learning, New J. Phys. 23 (2021) 103010

    2021

  28. [28]

    B.Gardas,M.M.Rams,J.Dziarmaga, Quantumneuralnetworkstosimulatemany-bodyquantumsystems, Phys.Rev.B98(2018)184304

    2018

  29. [29]

    and Yoo, Jae Hyeon and Isakov, Sergei V

    M. Broughton, et al., Tensorflow quantum: a software framework for quantum machine learning, arXiv 2003.02989 (2020)

    work page arXiv 2003

  30. [30]

    Tacchino, C

    F. Tacchino, C. Macchiavello, D. Gerace, D. Bajoni, An artificial neuron implemented on an actual quantum processor, npj Quantum Inf. 5 (2019) 1

    2019

  31. [31]

    Chakraborty, T

    S. Chakraborty, T. Das, S. Sutradhar, M. Das, S. Deb, An analytical review of quantum neural network models and relevant research, in: Proceedings of the Fifth International Conference on Communication and Electronics Systems (ICCES 2020), 2020, p. 48766

    2020

  32. [32]

    L.Alchieri,D.Badalotti,P.Bonardi,S.Bianco, Anintroductiontoquantummachinelearning:fromquantumlogictoquantumdeeplearning, Quantum Mach. Intell. 3 (2021) 28

    2021

  33. [33]

    R. Zhao, S. Wang, A review of quantum neural networks: methods, models, dilemma, arXiv 2109.01840 (2021)

    work page arXiv 2021

  34. [34]

    Mangini, F

    S. Mangini, F. Tacchino, D. Gerace, D. Bajoni, C. Macchiavello, Quantum computing models for artificial neural networks, Europhys. Lett. 134 (2021) 10002

    2021

  35. [35]

    Valdez, P

    F. Valdez, P. Melin, A review on quantum computing and deep learning algorithms and their applications, Soft Comput. 27 (2023) 13217– 13236

    2023

  36. [36]

    Abbas, et al., On quantum backpropagation, information reuse, and cheating measurement collapse, Adv

    A. Abbas, et al., On quantum backpropagation, information reuse, and cheating measurement collapse, Adv. Neural Inf. Process. Syst. 36 (2023) 44792–44819

    2023

  37. [37]

    J. R. McClean, S. Boixo, V. N. Smelyanskiy, R. Babbush, H. Neven, Barren plateaus in quantum neural network training landscapes, Nat. Commun. 9 (2018) 4812

    2018

  38. [38]

    Larocca, et al., Barren plateaus in variational quantum computing, Nat

    M. Larocca, et al., Barren plateaus in variational quantum computing, Nat. Rev. Phys. 7 (2025) 174–189

    2025

  39. [39]

    G. E. Crooks, Gradients of parameterized quantum gates using the parameter-shift rule and gate decomposition, arXiv 1905.13311 (2019)

    work page internal anchor Pith review Pith/arXiv arXiv 1905

  40. [40]

    Banchi, G

    L. Banchi, G. E. Crooks, Measuring analytic gradients of general quantum evolution with the stochastic parameter shift rule, Quantum 5 (2021) 386

    2021

  41. [41]

    Wierichs, J

    D. Wierichs, J. Izaac, C. Wang, C. Y.-Y. Lin, General parameter-shift rules for quantum gradients, Quantum 6 (2022) 677

    2022

  42. [42]

    Stokes, J

    J. Stokes, J. Izaac, N. Killoran, G. Carleo, Quantum natural gradient, Quantum 4 (2020) 269

    2020

  43. [43]

    Z. Tao, J. Wu, Q. Xia, Q. Li, Laws: look around and warm-start natural gradient descent for quantum neural networks, in: Proceedings of the 2023 IEEE International Conference on Quantum Software (QSW), IEEE, 2023, pp. 76–82

    2023

  44. [44]

    J. C. Spall, Multivariate stochastic approximation using a simultaneous perturbation gradient approximation, IEEE Trans. Autom. Control 37 (1992) 332–341

    1992

  45. [45]

    A.Kandala,etal.,Hardware-efficientvariationalquantumeigensolverforsmallmoleculesandquantummagnets,Nature549(2017)242–246

    2017

  46. [46]

    Lamata, U

    L. Lamata, U. Alvarez-Rodriguez, J. D. Martín-Guerrero, M. Sanz, E. Solano, Quantum autoencoders via quantum adders with genetic algorithms, Quantum Sci. Technol. 4 (2018) 014007

    2018

  47. [47]

    Z. Li, T. Xiao, X. Deng, G. Zeng, W. Li, Optimizing variational quantum neural networks based on collective intelligence, Mathematics 12 (2024) 1627

    2024

  48. [48]

    J. A. Nelder, R. Mead, A simplex method for function minimization, Comput. J. 7 (1965) 308–313

    1965

  49. [49]

    Aminpour, Y

    S. Aminpour, Y. Banad, S. Sharif, Strategic data re-uploads: a pathway to improved quantum classification data re-uploading strategies for improved quantum classifier performance, arXiv 2405.09377 (2024)

    work page arXiv 2024

  50. [50]

    Bonet-Monroig, et al., Performance comparison of optimization methods on variational quantum algorithms, Phys

    X. Bonet-Monroig, et al., Performance comparison of optimization methods on variational quantum algorithms, Phys. Rev. A 107 (2023) 032407

    2023

  51. [51]

    D.Dong,C.Chen,H.Li,T.-J.Tarn, Quantumreinforcementlearning, IEEETrans.Syst.ManCybern.PartBCybern.38(2008)1207–1220

    2008

  52. [52]

    G. D. Paparo, et al., Quantum speedup for active learning agents, Phys. Rev. X 4 (2014) 031002

    2014

  53. [53]

    Marias, et al., Quantum transfer learning for image classification, Quantum Mach

    K. Marias, et al., Quantum transfer learning for image classification, Quantum Mach. Intell. 3 (2021) 1–10

    2021

  54. [54]

    Bermejo, P

    P. Bermejo, P. Braccia, M. S. Rudolph, Z. Holmes, L. Cincio, M. Cerezo, Quantum convolutional neural networks are effectively classically simulable, PRX Quantum 7 (2026) 020304

    2026

  55. [55]

    Rebentrost, M

    P. Rebentrost, M. Mohseni, S. Lloyd, Quantum support vector machine for big data classification, Phys. Rev. Lett. 113 (2014) 130503

    2014

  56. [56]

    Lloyd, M

    S. Lloyd, M. Mohseni, P. Rebentrost, Quantum principal component analysis, Nat. Phys. 10 (2014) 631

    2014

  57. [57]

    Giovannetti, S

    V. Giovannetti, S. Lloyd, L. Maccone, Quantum random access memory, Phys. Rev. Lett. 100 (2008) 160501. Y. Sun, et al:Preprint submitted to ElsevierPage 41 of 47 Research progress on QNNs and QML

    2008

  58. [58]

    Araujo, F

    P. Araujo, F. Petruccione, A. J. Da Silva, Projective simulation artificial intelligence, Sci. Rep. 11 (2021) 6329

    2021

  59. [59]

    Larose, B

    R. Larose, B. Coyle, Physically motivated ansatz variational quantum algorithms, Phys. Rev. A 102 (2020) 032420

    2020

  60. [60]

    Z. Yang, X. Zhang, Entanglement-based quantum deep learning, New J. Phys. 22 (2020) 033041

    2020

  61. [61]

    Ballarin, S

    M. Ballarin, S. Mangini, S. Montangero, C. Macchiavello, R. Mengoni, Entanglement entropy production in quantum neural networks, Quantum 7 (2023) 1023

    2023

  62. [62]

    H. Shen, P. Zhang, Y.-Z. You, H. Zhai, Information scrambling in quantum neural networks, Phys. Rev. Lett. 124 (2020) 200504

    2020

  63. [63]

    Zhang, J

    B. Zhang, J. Liu, X.-C. Wu, L. Jiang, Q. Zhuang, Dynamical transition in controllable quantum neural networks with large depth, Nat. Commun. 15 (2024) 9354

    2024

  64. [64]

    Sannia, F

    A. Sannia, F. Tacchino, I. Tavernelli, G. L. Giorgi, R. Zambrini, Engineered dissipation to mitigate barren plateaus, npj Quantum Inf. 10 (2024) 81

    2024

  65. [65]

    Larocca, Barren plateaus variational quantum computing, npj Quantum Inf

    M. Larocca, Barren plateaus variational quantum computing, npj Quantum Inf. 10 (2024) 174–189

    2024

  66. [66]

    Friedrich, J

    L. Friedrich, J. Maziero, Quantum neural network with ensemble learning to mitigate barren plateaus and cost function concentration, Res. Sq. (2024)

    2024

  67. [67]

    Havlíček, et al., Supervised learning with quantum-enhanced feature spaces, Nature 567 (2019) 209–212

    V. Havlíček, et al., Supervised learning with quantum-enhanced feature spaces, Nature 567 (2019) 209–212

    2019

  68. [68]

    Li, D.-L

    W. Li, D.-L. Deng, Recent advances for quantum classifiers, Sci. China Phys. Mech. Astron. 65 (2022) 220301

    2022

  69. [69]

    Abbas, et al., The power of quantum neural networks, Nat

    A. Abbas, et al., The power of quantum neural networks, Nat. Comput. Sci. 1 (2021) 403–409

    2021

  70. [70]

    Zhao, X.-S

    C. Zhao, X.-S. Gao, Qdnn: deep neural networks with quantum layers, Quantum Mach. Intell. 3 (2021) 15

    2021

  71. [71]

    S. Wu, Y. Zhang, J. Li, Quantum data parallelism in quantum neural networks, Phys. Rev. Res. 7 (2025) 013177

    2025

  72. [72]

    Vidal, Classical simulation of infinite-size quantum lattice systems in one spatial dimension, Phys

    G. Vidal, Classical simulation of infinite-size quantum lattice systems in one spatial dimension, Phys. Rev. Lett. 98 (2007) 070201

    2007

  73. [73]

    Evenbly, G

    G. Evenbly, G. Vidal, Tensor network renormalization yields the multiscale entanglement renormalization ansatz, Phys. Rev. Lett. 115 (2015) 200401

    2015

  74. [74]

    Grant, Hierarchical quantum classifiers, npj Quantum Inf

    E. Grant, Hierarchical quantum classifiers, npj Quantum Inf. 4 (2018) 65

    2018

  75. [75]

    Pesah, et al., Absence of barren plateaus in quantum convolutional neural networks, Phys

    A. Pesah, et al., Absence of barren plateaus in quantum convolutional neural networks, Phys. Rev. X 11 (2021) 041011

    2021

  76. [76]

    S. Oh, J. Choi, J. Kim, A tutorial on quantum convolutional neural networks (qcnn), in: 2020 Int. Conf. Inf. Commun. Technol. Converg. (ICTC), IEEE, 2020, pp. 236–239

    2020

  77. [77]

    Mahmud, R

    J. Mahmud, R. Mashtura, S. A. Fattah, M. Saquib, Quantum convolutional neural networks with interaction layers for classification of classical data, Quantum Mach. Intell. 6 (2024) 1–20

    2024

  78. [78]

    M. C. Caro, et al., Generalization in quantum machine learning from few training data, Nat. Commun. 13 (2022) 4919

    2022

  79. [79]

    J.Herrmann,etal., Realizingquantumconvolutionalneuralnetworksonasuperconductingquantumprocessortorecognizequantumphases, Nat. Commun. 13 (2022) 4144

    2022

  80. [80]

    T. Hur, L. Kim, D. K. Park, Quantum convolutional neural network for classical data classification, Quantum Mach. Intell. 4 (2022) 3

    2022

Showing first 80 references.