IP Library Granted Patent US 12,518,192
Granted Patent B2
US 12,518,192 · App. 18/442,288 · Granted Jan 6, 2026

Quantum modulation classifier system and method

Inventors: Adrian Kaczmarczyk (Markham, CA); Wan Liu (Markham, CA); Ashkan Eshaghbeigi (Markham, CA); Lorne Swersky (Markham, CA)
Assignee: Qoherent Inc.
G06N10/60G01R29/06
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,518,192
App. No.
18/442,288
Filed
Feb 15, 2024
Granted
Jan 6, 2026
Kind
B2
Art Unit
2635
USPC
375/316
Abstract

A quantum modulation classifier. The quantum modulation classifier includes a trained quantum variational classifier including a plurality of qubits. The quantum variational classifier includes an embedding stage operable to apply a quantum embedding technique to embed a modulated radio signal, a variational stage operable to receive the modulated radio signal from the embedding stage and pass the modulated radio signal through a plurality of variational layers, and a measurement stage operable to receive the modulated radio signal from the variational stage and extract measurement results to classify the modulated radio signal.

Claims (33)

1 . A quantum modulation classifier, comprising:

a trained quantum variational classifier including a plurality of qubits and comprising:

an embedding stage operable to apply a quantum embedding technique to embed a modulated radio signal,

a variational stage operable to receive the modulated radio signal from the embedding stage and pass the modulated radio signal through a plurality of variational layers, and

a measurement stage operable to receive the modulated radio signal from the variational stage and extract measurement results to classify the modulated radio signal.

2 . The quantum modulation classifier of claim 1 , wherein the quantum variational classifier further comprises a preprocessing module operable to receive the modulated radio signal and apply a preprocessing step to transform the modulated radio signal into a representation that is more suitable for the quantum embedding technique prior to passing the modulated radio signal to the embedding stage.

3 . The quantum modulation classifier of claim 1 , wherein the quantum variational classifier is configured for re-embedding of the modulated radio signal in parallel.

4 . The quantum modulation classifier of claim 1 , wherein the quantum variational classifier is configured for re-embedding of the modulated radio signal in series.

5 . The quantum modulation classifier of claim 1 , wherein the radio signal is a frequency modulated signal.

6 . The quantum modulation classifier of claim 1 , wherein the quantum embedding technique is amplitude embedding.

7 . The quantum modulation classifier of claim 1 , wherein the quantum embedding technique is angle embedding.

8 . The quantum modulation classifier of claim 1 , wherein the variational stage includes at least twenty variational layers.

9 . A quantum modulation classifier, comprising:

a radio signal receiver operable to measure a modulated radio signal; and

a trained quantum variational classifier communicatively coupled to the radio signal receiver to receive the modulated radio signal, the quantum variational classifier including a plurality of qubits and comprising:

an embedding stage operable to apply a quantum embedding technique to embed the modulated radio signal,

a variational stage operable to receive the modulated radio signal from the embedding stage and pass the modulated radio signal through a plurality of variational layers, and

a measurement stage operable to receive the modulated radio signal from the variational stage and extract measurement results to classify the modulated radio signal.

10 . The quantum modulation classifier of claim 9 , wherein the quantum variational classifier further comprises a preprocessing module operable to receive the modulated radio signal and apply a preprocessing step to transform the modulated radio signal into a representation that is more suitable for the quantum embedding technique prior to passing the modulated radio signal to the embedding stage.

11 . The quantum modulation classifier of claim 9 , wherein the quantum variational classifier is configured for re-embedding of the modulated radio signal in parallel.

12 . The quantum modulation classifier of claim 9 , wherein the quantum variational classifier is configured for re-embedding of the modulated radio signal in series.

13 . The quantum modulation classifier of claim 9 , wherein the modulated radio signal is a frequency modulated signal.

14 . A quantum modulation classification method, comprising:

receiving a modulated radio signal

embedding the modulated radio signal using an embedding stage of a quantum variational classifier;

passing the embedded modulated radio signal through a variational stage of the quantum variational classifier;

extracting measurement results from the embedded modulated radio signal passed through the variational stage using a measurement stage of the quantum variational classifier; and

classifying the modulated radio signal using the measurement results.

15 . The quantum modulation classification method of claim 14 , further comprising applying a preprocessing step to transform the modulated radio signal into a representation that is more suitable for a quantum embedding technique prior to embedding the modulated radio signal.

16 . The quantum modulation classification method of claim 14 , further comprising re-embedding the modulated radio signal in parallel.

17 . The quantum modulation classification method of claim 14 , further comprising re-embedding the modulated radio signal in series.

18 . The quantum modulation classification method of claim 14 , wherein embedding the modulated radio signal includes performing amplitude embedding of the modulated radio signal.

19 . The quantum modulation classification method of claim 14 , wherein embedding the modulated radio signal includes performing angle embedding of the modulated radio signal.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded May 8, 2024
From: KACZMARCZYK, ADRIAN; LIU, WAN; ESHAGHBEIGI, ASHKAN; SWERSKY, LORNE
To: QOHERENT INC.
Reel/Frame 067345/0082 →
Continuity (2)
Provisional Application 63450329 · Mar 6, 2023
Related Publication 20240428113A1 · Dec 26, 2024
References Cited (84)
US 7428270B1 · Dubuc · 2008 [cited by examiner]
US 10572830B2 · O'Shea · 2020 [cited by applicant]
US 11032014B2 · O'Shea et al. · 2021 [cited by applicant]
US 11210368B2 · Caglar · 2021 [cited by applicant]
US 11270217B2 · Tee et al. · 2022 [cited by applicant]
US 20100150222A1 · Meyers et al. · 2010 [cited by applicant]
US 20190095756A1 · Agrawal et al. · 2019 [cited by applicant]
US 20200265333A1 · Horesh et al. · 2020 [cited by applicant]
US 20210150401A1 · Zhuang et al. · 2021 [cited by applicant]
US 20210256416A1 · Bocharov · 2021 [cited by examiner]
US 20210264199A1 · Walters et al. · 2021 [cited by applicant]
US 20210295107A1 · Krishna et al. · 2021 [cited by applicant]
US 20210334626A1 · Hang et al. · 2021 [cited by applicant]
US 20220012618A1 · Salim et al. · 2022 [cited by applicant]
US 20230073231A1 · Sogabe et al. · 2023 [cited by applicant]
CA 3088650A1 · 2019 [cited by applicant]
CA 3112817A1 · 2020 [cited by applicant]
CN 109800883A · 2019 [cited by applicant]
CN 109067473B · 2019 [cited by applicant]
CN 110009108A · 2019 [cited by applicant]
CN 110879105A · 2020 [cited by applicant]
CN 111709530A · 2020 [cited by applicant]
CN 112001498A · 2020 [cited by applicant]
CN 110149207B · 2021 [cited by applicant]
CN 112464003A · 2021 [cited by applicant]
CN 113052317A · 2021 [cited by applicant]
CN 113379059A · 2021 [cited by applicant]
CN 113449778A · 2021 [cited by applicant]
CN 113676266A · 2021 [cited by applicant]
CN 114169469A · 2022 [cited by applicant]
CN 114358317A · 2022 [cited by applicant]
CN 114358318A · 2022 [cited by applicant]
CN 114358319A · 2022 [cited by applicant]
CN 114399053A · 2022 [cited by applicant]
CN 114444701A · 2022 [cited by applicant]
CN 114444702A · 2022 [cited by applicant]
CN 114565096A · 2022 [cited by applicant]
CN 108701263B · 2022 [cited by applicant]
CN 114358295B · 2022 [cited by applicant]
CN 114663690A · 2022 [cited by applicant]
CN 114667710A · 2022 [cited by applicant]
CN 114819163A · 2022 [cited by applicant]
CN 113379060B · 2022 [cited by applicant]
CN 115293254A · 2022 [cited by applicant]
CN 115374948A · 2022 [cited by applicant]
CN 115409189A · 2022 [cited by applicant]
CN 115438790A · 2022 [cited by applicant]
CN 115618232A · 2023 [cited by applicant]
CN 115630705A · 2023 [cited by applicant]
CN 115761384A · 2023 [cited by applicant]
CN 115828999A · 2023 [cited by applicant]
CN 115860130A · 2023 [cited by applicant]
CN 113408731B · 2023 [cited by applicant]
CN 113449778B · 2023 [cited by applicant]
CN 115936134A · 2023 [cited by applicant]
EP 1445890A1 · 2004 [cited by applicant]
IN 202147044181A · 2021 [cited by applicant]
IN 202141009256A · 2022 [cited by applicant]
JP 4775820B2 · 2011 [cited by applicant]
JP 6165638B2 · 2017 [cited by applicant]
JP 2021026370A · 2021 [cited by applicant]
JP 6979661B2 · 2021 [cited by applicant]
JP 2021193615A · 2021 [cited by applicant]
JP 2023039444A · 2023 [cited by applicant]
KR 20210081859A · 2021 [cited by applicant]
KR 20220015308A · 2022 [cited by applicant]
WO 2017131081A1 · 2017 [cited by applicant]
WO 2017197008A1 · 2017 [cited by applicant]
WO 2019163866A1 · 2019 [cited by applicant]
WO 2020077288A1 · 2020 [cited by applicant]
WO 2020167466A1 · 2020 [cited by applicant]
WO 2020201002A1 · 2020 [cited by applicant]
WO 2020263146A1 · 2020 [cited by applicant]
WO 2021238279A1 · 2021 [cited by applicant]
WO 2021243454A1 · 2021 [cited by applicant]
WO 2022106003A1 · 2022 [cited by applicant]
WO 2023287333A1 · 2023 [cited by applicant]
Wu, Y. et al., “Radio Signal Classication by Adversarially Robust Quantum Machine Learning”. Arxiv.org, Dec. 13, 2023 (Dec. 13, 2023), [online] [retrieved on May 16, 2024 (May 16, 2024)]. Retrieved from the Internet: <h… [cited by applicant]
Yen-Chi Chen, S. et al., “Variational Quantum Circuits for Deep Reinforcement Learning”. Arxiv.org, Jul. 20, 2020 (Jul. 20, 2020), [online] [retrieved on May 16, 2024 (May 16, 2024)]. Retrieved from the Internet: <https… [cited by applicant]
Kuar, A. et al., “A comprehensive survey on machine learning approaches for dynamic spectrum access in cognitive radio networks.”. Journal of Experimental & Theoretical Artificial Intelligence, Feb. 2022 (Feb. 2022), vo… [cited by applicant]
International Search Report (ISR) & Written Opinion (WO) mailed Jun. 13, 2024 in PCT/CA2024/050195 (6 pages). [cited by applicant]
Möttonen et al., “Transformation of quantum states using uniformly controlled rotations”, Quantum Information and Computation, vol. 5, No. 6, pp. 467-473, Sep. 2005. [cited by applicant]
Schuld, Maria, et al. “Circuit-centric quantum classifiers.” Physical Review A 101.3 (2020): 032308. [cited by applicant]
D. P. Kingma and J. Ba, “Adam: A method for stochastic optimization”, CoRR, vol. abs/1412.6980, 2014. [Online]. Available: http://arxiv.org/abs/1412.6980. [cited by applicant]