國立高雄大學圖資館 |

登入

回首頁

Quantum Circuit Integration in Diffusion Models for Image Synthesis /

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Quantum Circuit Integration in Diffusion Models for Image Synthesis /Matthew Morais.
作者:	Morais, Matthew,
面頁冊數:	1 electronic resource (137 pages)
附註:	Source: Dissertations Abstracts International, Volume: 87-06, Section: B.
附註:	Advisors: Elbasheer, Mohamed Committee members: Etemadi, Amir; El-Yousseff, Rami.
Contained By:	Dissertations Abstracts International87-06B.
標題:	Quantum physics.
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=32284943
ISBN:	9798270219642

Quantum Circuit Integration in Diffusion Models for Image Synthesis /
Morais, Matthew,

Quantum Circuit Integration in Diffusion Models for Image Synthesis /Matthew Morais. - 1 electronic resource (137 pages)

Source: Dissertations Abstracts International, Volume: 87-06, Section: B.

The sequential inference process of modern diffusion models causes a wide range of significant computational challenges in both implementation and deployment. This creates bottlenecks that prevent parallelization and result in slowed training convergence times. These models also struggle when trained on noisy or biased data, making them less useful in a resource constrained environment or real time applications.This praxis demonstrates that novel quantum loss functions and circuit architectures improve the convergence of diffusion model training and sampling quality through quantum probabilistic measurements. This architectural approach demonstrates a useful way to build quantum enhanced generative artificial intelligence. The research develops and implements quantum specific loss functions leveraging fidelity, trace distance, and quantum divergence measures, while methodically examining quantum circuit design strategies such as entanglement patterns and label encoding methods.A hybrid quantum-classical diffusion model was constructed using PennyLane's quantum simulation framework, integrating variational quantum circuits within a denoising diffusion architecture. The model produces quantum measurement probability distributions as outputs, making it easy to use with current simulators and, eventually, real quantum hardware. The MNIST Digits dataset reduced to 8x8 pixel resolution was used for the both investigating the circuit design space and for comparative validation to other works. The performance was measured using the Fréchet Inception Distance (FID), Structural Similarity Index (SSIM), and Peak Signal-to-Noise Ratio (PSNR) metrics. Some higher resolution datasets were also used for validation, such as the MNIST, MNIST Fashion, and CIFAR10 datasets. The high contrast, single channel datasets, like MNIST, demonstrated broader applicability of this approach to higher resolution data. The multichannel, more natural imagery from the CIFAR10 dataset indicated nuances between generation task and architectural decisions that may explain the observed reduction in performance.Results from this research demonstrate design guidance for quantum integration in diffusion models targeted for MNIST-like image denoising tasks. The ~28% improvements in FID, SSIM, and PSNR over similar works, illustrate how tailored quantum loss functions and optimized circuit architectures can achieve competitive performance in denoising tasks. This research contributes foundational insights for quantum enhanced generative modeling; developing algorithms ready for deployment on physical quantum hardware as the technology evolves.

English

ISBN: 9798270219642Subjects--Topical Terms:

766192
Quantum physics.
Subjects--Index Terms:

Diffusion

Quantum Circuit Integration in Diffusion Models for Image Synthesis /
LDR:04160nmm a22004453i 4500 001 693781
005 20260511063023.5
006 m o d
007 cr|nu||||||||
008 260819s2026 miu||||||m |||||||eng d
020 $a 9798270219642
035 $a (MiAaPQD)AAI32284943
035 $a AAI32284943
040 $a MiAaPQD $b eng $c MiAaPQD $e rda
100 1 $a Morais, Matthew, $e author. $3 1010457
245 1 0 $a Quantum Circuit Integration in Diffusion Models for Image Synthesis / $c Matthew Morais.
264 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2026
300 $a 1 electronic resource (137 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Dissertations Abstracts International, Volume: 87-06, Section: B.
500 $a Advisors: Elbasheer, Mohamed Committee members: Etemadi, Amir; El-Yousseff, Rami.
502 $b D.Engr. $c The George Washington University $d 2026.
520 $a The sequential inference process of modern diffusion models causes a wide range of significant computational challenges in both implementation and deployment. This creates bottlenecks that prevent parallelization and result in slowed training convergence times. These models also struggle when trained on noisy or biased data, making them less useful in a resource constrained environment or real time applications.This praxis demonstrates that novel quantum loss functions and circuit architectures improve the convergence of diffusion model training and sampling quality through quantum probabilistic measurements. This architectural approach demonstrates a useful way to build quantum enhanced generative artificial intelligence. The research develops and implements quantum specific loss functions leveraging fidelity, trace distance, and quantum divergence measures, while methodically examining quantum circuit design strategies such as entanglement patterns and label encoding methods.A hybrid quantum-classical diffusion model was constructed using PennyLane's quantum simulation framework, integrating variational quantum circuits within a denoising diffusion architecture. The model produces quantum measurement probability distributions as outputs, making it easy to use with current simulators and, eventually, real quantum hardware. The MNIST Digits dataset reduced to 8x8 pixel resolution was used for the both investigating the circuit design space and for comparative validation to other works. The performance was measured using the Fréchet Inception Distance (FID), Structural Similarity Index (SSIM), and Peak Signal-to-Noise Ratio (PSNR) metrics. Some higher resolution datasets were also used for validation, such as the MNIST, MNIST Fashion, and CIFAR10 datasets. The high contrast, single channel datasets, like MNIST, demonstrated broader applicability of this approach to higher resolution data. The multichannel, more natural imagery from the CIFAR10 dataset indicated nuances between generation task and architectural decisions that may explain the observed reduction in performance.Results from this research demonstrate design guidance for quantum integration in diffusion models targeted for MNIST-like image denoising tasks. The ~28% improvements in FID, SSIM, and PSNR over similar works, illustrate how tailored quantum loss functions and optimized circuit architectures can achieve competitive performance in denoising tasks. This research contributes foundational insights for quantum enhanced generative modeling; developing algorithms ready for deployment on physical quantum hardware as the technology evolves.
546 $a English
590 $a School code: 0075
650 4 $a Quantum physics. $3 766192
650 4 $a Computer science. $3 199325
650 4 $a Information technology. $3 184390
653 $a Diffusion
653 $a Machine learning
653 $a Quantum circuits
653 $a Fréchet Inception Distance
653 $a Structural Similarity Index
690 $a 0800
690 $a 0489
690 $a 0599
690 $a 0984
710 2 $a The George Washington University. $b Data Science. $e degree granting institution. $3 1010458
720 1 $a Elbasheer, Mohamed $e degree supervisor.
773 0 $t Dissertations Abstracts International $g 87-06B.
790 $a 0075
791 $a D.Engr.
792 $a 2026
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=32284943