Pith. sign in

REVIEW 7 cited by

Quantum-Inspired Machine Learning: a Survey

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2308.11269 v2 pith:I46I4CQW submitted 2023-08-22 cs.LG quant-ph

classification cs.LGquant-ph
keywords qimllearningmachinequantumfieldfuturesurveyclassical
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Quantum-inspired Machine Learning (QiML) is a burgeoning field, receiving global attention from researchers for its potential to leverage principles of quantum mechanics within classical computational frameworks. However, current review literature often presents a superficial exploration of QiML, focusing instead on the broader Quantum Machine Learning (QML) field. In response to this gap, this survey provides an integrated and comprehensive examination of QiML, exploring QiML's diverse research domains including tensor network simulations, dequantized algorithms, and others, showcasing recent advancements, practical applications, and illuminating potential future research avenues. Further, a concrete definition of QiML is established by analyzing various prior interpretations of the term and their inherent ambiguities. As QiML continues to evolve, we anticipate a wealth of future developments drawing from quantum mechanics, quantum computing, and classical machine learning, enriching the field further. This survey serves as a guide for researchers and practitioners alike, providing a holistic understanding of QiML's current landscape and future directions.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 7 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. QiVC-Net: Quantum-Inspired Variational Convolutional Network, with Application to Biosignal Classification

    cs.LG 2025-11 conditional novelty 6.0 of 10

    Rotating convolutional weights in a learned low-dimensional subspace during training yields 97.84% and 97.89% accuracy on the CinC 2016 and CirCor 2022 phonocardiogram benchmarks.

  2. Boosting Classification with Quantum-Inspired Augmentations

    cs.CV 2025-06 conditional novelty 6.0 of 10

    The paper reports that quantum-inspired Bloch rotations, combined with classical flips and perfect rotations, improve ImageNet Top-1 accuracy by about 3% relative to classical augmentation alone.

  3. Noise-Induced Thermalization in Quantum Systems

    quant-ph 2025-12 conditional novelty 5.0 of 10

    Interleaving random or phase-flip noise with Hamiltonian evolution accelerates—and for integrable chains enables—local convergence to Gibbs states in small spin-chain simulations.

  4. Quantum Entrepreneurship Lab: Training a Future Workforce for the Quantum Industry

    physics.ed-ph 2025-05 unverdicted novelty 5.0 of 10

    The Quantum Entrepreneurship Lab at TUM is a project-based course pairing technical and business students to work on quantum research topics and craft startup pitches.

  5. Quantum-inspired Embeddings Projection and Similarity Metrics for Representation Learning

    cs.CL 2025-01 conditional novelty 5.0 of 10

    A quantum-inspired, parameter-light projection head compressing BERT embeddings to 256 dimensions matches a classical dense head on TREC passage reranking and improves on small training sets.

  6. Quantum-Enhanced Transformers for Robust Acoustic Scene Classification in IoT Environments

    eess.AS 2025-01 reject novelty 4.0 of 10

    A quantum-inspired transformer with a quantum VAE augmentation step is claimed to improve acoustic scene classification accuracy on the TUT 2016 benchmark by over 5% in the best case.

  7. Training-free Quantum-Inspired Image Edge Extraction Method

    cs.CV 2025-01 reject novelty 2.0 of 10

    A training-free edge detector combining Sobel, heat-equation diffusion, and Canny/Laplacian fusion claims SOTA scores, but lacks reproducible evaluation and mislabels the diffusion equation as Schrödinger's.

Pith tools