analiza aiqbench
This research introduces a hybrid classical-quantum framework that applies quantum-inspired techniques, such as amplitude encoding and stabilizer codes, to improve image classification efficiency on standard GPU workstations. By utilizing a mixture of experts approach, the method reduces feature extraction overhead while cutting prediction failure rates by approximately half compared to individual expert models. The study demonstrates practical viability for near-term applications without requiring full-scale quantum hardware execution.
Image classification via a quantum-inspired strategy involving a mixture of experts
arXiv:2607.07754v2 Announce Type: replace-cross Abstract: Pattern recognition problems arise in a variety of physical image processing situations, and convolutional neural networks are a popular scheme for the required feature extraction and classification tasks. The classical networks use diffusion-based smearing and block-wise pooling to downsample the image data and capture important structural features. In this work, we propose and demonstrate a more efficient quantum-inspired strategy involving a mixture of experts. It is a hybrid classical-quantum framework. The quantum part consists of amplitude encoding of the images, convolution using local unitary operations, multiple experts processing the same image with different parameters, and feature extraction using quantum stabiliser codes. The classical part then jointly processes the features extracted by different experts using a standard fully connected neural network for image class prediction. Using MNIST and Fashion-MNIST datasets as benchmarks, we demonstrate that the joint expert analysis outperforms the individual expert one, as well as reduces the failure rate of image class prediction by around a factor of two. The overhead of our quantum-inspired strategy is only moderate on GPU workstations, which makes our proposal a practical alternative to existing classical schemes. We also point out how the quantum part of our framework can be executed on a quantum processor.
Abstract:Pattern recognition problems arise in a variety of physical image processing situations, and convolutional neural networks are a popular scheme for the required feature extraction and classification tasks. The classical networks use diffusion-based smearing and block-wise pooling to downsample the image data and capture important structural features. In this work, we propose and demonstrate a more efficient quantum-inspired strategy involving a mixture of experts. It is a hybrid classical-quantum framework. The quantum part consists of amplitude encoding of the images, convolution using local unitary operations, multiple experts processing the same image with different parameters, and feature extraction using quantum stabiliser codes. The classical part then jointly processes the features extracted by different experts using a standard fully connected neural network for image class prediction. Using MNIST and Fashion-MNIST datasets as benchmarks, we demonstrate that the joint expert analysis outperforms the individual expert one, as well as reduces the failure rate of image class prediction by around a factor of two. The overhead of our quantum-inspired strategy is only moderate on GPU workstations, which makes our proposal a practical alternative to existing classical schemes. We also point out how the quantum part of our framework can be executed on a quantum processor.
14 pages, 18 figures, comments welcome (v2) The number of features extracted from the images is considerably reduced, which simplifies the subsequent classification. The results are essentially the same
Machine Learning (cs.LG); Quantum Physics (quant-ph)
arXiv:2607.07754 [cs.LG]
(or arXiv:2607.07754v2 [cs.LG] for this version)
Text integral sub licența deschisă a publicației · 244 cuvinte
Subiecte conexe
Humanity’s Last Invention — Richard Socher of Recursive
Latent Space · 14 sept. 2026
Game Design Creativity evals
LessWrong · 12 oct. 2026
Digital States 2026: AI Moves From Experiment to Infrastructure
govtech.com · 24 sept. 2026
Complete Guide to Thinking Machines Inkling
Analytics Vidhya · 20 iul. 2026