Hybrid Quantum-inspired Resnet and Densenet for Pattern Recognition
- URL: http://arxiv.org/abs/2403.05754v6
- Date: Tue, 18 Feb 2025 08:03:59 GMT
- Title: Hybrid Quantum-inspired Resnet and Densenet for Pattern Recognition
- Authors: Andi Chen, Hua-Lei Yin, Zeng-Bing Chen, Shengjun Wu,
- Abstract summary: We propose two hybrid quantum-inspired neural networks with adaptive residual and dense connections respectively for pattern recognition.
We show the potential superiority of our hybrid models to prevent gradient explosion owing to the quantum-inspired layers.
- Score: 1.0499611180329804
- License:
- Abstract: In this paper, we propose two hybrid quantum-inspired neural networks with adaptive residual and dense connections respectively for pattern recognition. We explain the frameworks of the symmetrical circuit models in the quantum-inspired layers in our hybrid models. We also illustrate the potential superiority of our hybrid models to prevent gradient explosion owing to the quantum-inspired layers. Groups of numerical experiments on generalization power show that our hybrid models possess roughly the same level of generalization power as the pure classical models with different noisy datasets utilized. Furthermore, the comparison on generalization ability between our hybrid models and a state-of-the-art hybrid quantum-classical convolutional network demonstrates 3%-4% higher accuracy of our hybrid densely-connected model than the hybrid quantum-classical network. Simultaneously, in terms of groups of experiment on robustness, the results demonstrate that our two hybrid models outperform pure classical models notably in resistance to parameter attacks with various asymmetric noises. They also indicate the superiority of our densely-connected hybrid model over the hybrid quantum-classical network under both symmetrical and asymmetrical attacks. Furthermore, an ablation study indicate that the recognition accuracy of our two hybrid models is 2%-3% higher than that of the traditional quantum-inspired neural network without residual or dense connection. Eventually, we discuss the application scenarios of our hybrid models by analyzing their computational complexities.
Related papers
- Quantum Latent Diffusion Models [65.16624577812436]
We propose a potential version of a quantum diffusion model that leverages the established idea of classical latent diffusion models.
This involves using a traditional autoencoder to reduce images, followed by operations with variational circuits in the latent space.
The results demonstrate an advantage in using a quantum version, as evidenced by obtaining better metrics for the images generated by the quantum version.
arXiv Detail & Related papers (2025-01-19T21:24:02Z) - Modeling Nonlinear Oscillator Networks Using Physics-Informed Hybrid Reservoir Computing [0.0]
We investigate hybrid reservoir computing, combining reservoir computing with "expert" analytical models.
We show that hybrid reservoir computers generally outperform standard reservoir computers.
There is good performance for dynamical regimes not accessible to the expert model, demonstrating the contribution of the reservoir.
arXiv Detail & Related papers (2024-11-07T15:09:23Z) - An ensemble framework approach of hybrid Quantum convolutional neural networks for classification of breast cancer images [2.1659912179830023]
Quantum neural networks are deemed suitable to replace classical neural networks in their ability to learn and scale up network models.
Medical image classification pertains well to applications in deep learning, particularly, convolutional neural networks.
arXiv Detail & Related papers (2024-09-24T10:43:27Z) - Towards Efficient Quantum Hybrid Diffusion Models [68.43405413443175]
We propose a new methodology to design quantum hybrid diffusion models.
We propose two possible hybridization schemes combining quantum computing's superior generalization with classical networks' modularity.
arXiv Detail & Related papers (2024-02-25T16:57:51Z) - Adversarial attacks on hybrid classical-quantum Deep Learning models for
Histopathological Cancer Detection [0.0]
The study emphasizes two primary applications of hybrid classical-quantum Deep Learning models.
We compare the performance accuracy of the classical model with the hybrid classical-quantum model using pennylane default quantum simulator.
arXiv Detail & Related papers (2023-09-08T06:37:54Z) - A Framework for Demonstrating Practical Quantum Advantage: Racing
Quantum against Classical Generative Models [62.997667081978825]
We build over a proposed framework for evaluating the generalization performance of generative models.
We establish the first comparative race towards practical quantum advantage (PQA) between classical and quantum generative models.
Our results suggest that QCBMs are more efficient in the data-limited regime than the other state-of-the-art classical generative models.
arXiv Detail & Related papers (2023-03-27T22:48:28Z) - Photonic Quantum Computing For Polymer Classification [62.997667081978825]
Two polymer classes visual (VIS) and near-infrared (NIR) are defined based on the size of the polymer gaps.
We present a hybrid classical-quantum approach to the binary classification of polymer structures.
arXiv Detail & Related papers (2022-11-22T11:59:52Z) - Hybrid Classical-Quantum Deep Learning Models for Autonomous Vehicle
Traffic Image Classification Under Adversarial Attack [2.6545358349290415]
Traffic sign images can be misclassified by an adversarial attack on machine learning models used by AVs for traffic sign recognition.
To make classification models resilient against adversarial attacks, we used a hybrid deep-learning model with both the quantum and classical layers.
Our goal is to study the hybrid deep-learning architecture for classical-quantum transfer learning models to support the current era of intermediate-scale quantum technology.
arXiv Detail & Related papers (2021-08-02T19:00:20Z) - Hyperbolic Neural Networks++ [66.16106727715061]
We generalize the fundamental components of neural networks in a single hyperbolic geometry model, namely, the Poincar'e ball model.
Experiments show the superior parameter efficiency of our methods compared to conventional hyperbolic components, and stability and outperformance over their Euclidean counterparts.
arXiv Detail & Related papers (2020-06-15T08:23:20Z) - Kernel and Rich Regimes in Overparametrized Models [69.40899443842443]
We show that gradient descent on overparametrized multilayer networks can induce rich implicit biases that are not RKHS norms.
We also demonstrate this transition empirically for more complex matrix factorization models and multilayer non-linear networks.
arXiv Detail & Related papers (2020-02-20T15:43:02Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.