arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2403.05754cs.LGcs.ET
收藏

混合量子启发式Resnet与Densenet用于模式识别

Hybrid Quantum-inspired Resnet and Densenet for Pattern Recognition

Institute for Brain Sciences(脑科学研究院);Kuang Yaming Honors School, Nanjing University(南京大学匡杨荣誉学院);National Laboratory of Solid State Microstructures(固态微结构国家实验室);School of Physics, Collaborative Innovation Center of Advanced Microstructures(物理学院,先进微结构协同创新中心);School of Physics(物理学院);Beijing Key Laboratory of Opto-Electronic Functional Materials(北京光学材料重点实验室);Micro-Nano Devices, Key Laboratory of Quantum State Construction(微纳器件,量子态构造重点实验室);Manipulation(Ministry of Education), Renmin University of China(操控(教育部),中国人民大学)

Andi Chen, Hua-Lei Yin, Zeng-Bing Chen, Shengjun Wu

AI总结:

提出两种混合量子启发式神经网络(自适应残差和密集连接),用于模式识别,在泛化、鲁棒性和准确率上优于经典及混合量子-经典模型,并分析计算复杂度。

摘要:

在本文中,我们提出了两种混合量子启发式神经网络,分别具有自适应残差连接和密集连接,用于模式识别。我们解释了混合模型中量子启发层中对称电路模型的框架。我们还说明了我们的混合模型在防止梯度爆炸方面的潜在优势,这得益于量子启发层中的正弦和余弦函数。关于泛化能力的多组数值实验表明,在使用不同噪声数据集的情况下,我们的混合模型与纯经典模型相当。此外,我们的混合模型与最先进的混合量子-经典卷积网络的比较表明,我们的混合密集连接模型的准确率比混合量子-经典网络高出3%-4%。另外,与其他两种混合量子启发式残差网络相比,我们的混合模型在具有非对称噪声的图像数据集上展示了略高的准确率。同时,在鲁棒性实验方面,结果表明我们的两个混合模型在抵抗具有各种非对称噪声的对抗性参数攻击方面显著优于纯经典模型。它们还表明我们的密集连接混合模型在对称和非对称攻击方面都略优于混合量子-经典网络。同时,我们的两个混合模型的准确率略高于两个混合量子启发式残差网络。此外,一项消融研究表明,我们的两个混合模型的识别准确率比没有残差或密集连接的传统量子启发式神经网络高出2%-3%。最后,我们通过分析计算复杂度来讨论混合模型的应用场景。

英文摘要:

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 sine and cosine functions in the quantum-inspired layers. Groups of numerical experiments on generalization power showcase that our hybrid models are comparable to the pure classical models with different noisy datasets utilized. Furthermore, the comparison 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. Additionally, compared with other two hybrid quantum-inspired residual networks, our hybrid models showcase a little higher accuracy on image datasets with asymmetrical noises. Simultaneously, in terms of groups of robustness experiments, the outcomes demonstrate that our two hybrid models outperform pure classical models notably in resistance to adversarial parameter attacks with various asymmetrical noises. They also indicate the slight superiority of our densely-connected hybrid model over the hybrid quantum-classical network to both symmetrical and asymmetrical attacks. Meanwhile, the accuracy of our two hybrid models is a little bit higher than that of the two hybrid quantum-inspired residual networks. In addition, 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 complexity.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑