Formal state space models of quantum control systems are deduced and a scheme to establish formal state space models via quantization could been obtained for quantum control systems is proposed. State evolution of qua...Formal state space models of quantum control systems are deduced and a scheme to establish formal state space models via quantization could been obtained for quantum control systems is proposed. State evolution of quantum control systems must accord with Schrdinger equations, so it is foremost to obtain Hamiltonian operators of systems. There are corresponding relations between operators of quantum systems and corresponding physical quantities of classical systems, such as momentum, energy and Hamiltonian, so Schrdinger equation models of corresponding quantum control systems via quantization could been obtained from classical control systems, and then establish formal state space models through the suitable transformation from Schrdinger equations for these quantum control systems. This method provides a new kind of path for modeling in quantum control.展开更多
作为机器学习领域的研究新方向,多无源域适应旨在将多个源域模型中的知识迁移到目标域,以实现对目标域样本的准确预测。本质上,解决多无源域适应的关键在于如何量化多个源模型对目标域的贡献,并利用源模型中的多样性知识来适应目标域。...作为机器学习领域的研究新方向,多无源域适应旨在将多个源域模型中的知识迁移到目标域,以实现对目标域样本的准确预测。本质上,解决多无源域适应的关键在于如何量化多个源模型对目标域的贡献,并利用源模型中的多样性知识来适应目标域。为了应对上述问题,提出了一种基于源模型贡献量化(Source Model Contribution Quantizing,SMCQ)的多无源域适应方法。具体而言,提出了源模型可转移性感知,以量化源模型的可转移性贡献,从而为目标域模型有效地分配源模型的自适应权重。其次,引入了信息最大化方法,以缩小跨域的分布差异,并解决模型退化的问题。然后,提出了可信划分全局对齐方法,该方法用于划分高可信和低可信样本,以应对域差异引起的嘈杂环境,并有效降低标签分配错误的风险。此外,还引入了样本局部一致性损失,以减小伪标签噪声对低可信样本聚类错误的影响。最后,在多个数据集上进行实验,验证了所提方法的有效性。展开更多
为快速、方便、正确地将卷积神经网络部署于嵌入式平台实现硬件加速,并解决在硬件部署时遇到的模型计算量大、占用存储多、部署困难等问题,提出一种基于ResNet模型的通道剪枝结合混合精度量化的方法,将模型压缩后,部署于神经网络处理器(...为快速、方便、正确地将卷积神经网络部署于嵌入式平台实现硬件加速,并解决在硬件部署时遇到的模型计算量大、占用存储多、部署困难等问题,提出一种基于ResNet模型的通道剪枝结合混合精度量化的方法,将模型压缩后,部署于神经网络处理器(neural processing unit, NPU)实现硬件加速。在传统的模型剪枝和量化基础上,采用通道剪枝结合混合精度量化的方法,在保证模型性能的前提下最大程度压缩网络模型。硬件部署推理实验结果表明,该方法可实现对原始模型压缩7.75倍,模型推理速度提升2.55倍,实验验证了该方法对ResNet模型的压缩和硬件推理加速具有一定效果。展开更多
In this paper, a new amplitude quantization synthesis method for ultralow sidelobe phased arrays is proposed, which is based on the constrained nonlinear optimization algorithm. By introducing a set of critical constr...In this paper, a new amplitude quantization synthesis method for ultralow sidelobe phased arrays is proposed, which is based on the constrained nonlinear optimization algorithm. By introducing a set of critical constraint conditions into the optimization model, we can directly quantize the amplitude distribution instead of replacing it with a continuous equivalent aperture antenna. The mutual coupling and the element patterns are also considered in the quantization synthesis. Finally, some array simulation results are given to show the effectiveness of the method.展开更多
随着人工智能的发展,深度神经网络成为多种模式识别任务中必不可少的工具,由于深度卷积神经网络(CNN)参数量巨大、计算复杂度高,将它部署到计算资源和存储空间受限的边缘计算设备上成为一项挑战。因此,深度网络压缩成为近年来的研究热...随着人工智能的发展,深度神经网络成为多种模式识别任务中必不可少的工具,由于深度卷积神经网络(CNN)参数量巨大、计算复杂度高,将它部署到计算资源和存储空间受限的边缘计算设备上成为一项挑战。因此,深度网络压缩成为近年来的研究热点。低秩分解与向量量化是深度网络压缩中重要的两个研究分支,其核心思想都是通过找到原网络结构的一种紧凑型表达,从而降低网络参数的冗余程度。通过建立联合压缩框架,提出一种基于低秩分解和向量量化的深度网络压缩方法——可量化的张量分解(QTD)。该方法能够在网络低秩结构的基础上实现进一步的量化,从而得到更大的压缩比。在CIFAR-10数据集上对经典ResNet和该方法进行验证的实验结果表明,QTD能够在准确率仅损失1.71个百分点的情况下,将网络参数量压缩至原来的1%。而在大型数据集ImageNet上把所提方法与基于量化的方法PQF(Permute,Quantize,and Fine-tune)、基于低秩分解的方法TDNR(Tucker Decomposition with Nonlinear Response)和基于剪枝的方法CLIP-Q(Compression Learning by In-parallel Pruning-Quantization)进行比较与分析的实验结果表明,QTD能够在相同压缩范围下实现更好的分类准确率。展开更多
文摘Formal state space models of quantum control systems are deduced and a scheme to establish formal state space models via quantization could been obtained for quantum control systems is proposed. State evolution of quantum control systems must accord with Schrdinger equations, so it is foremost to obtain Hamiltonian operators of systems. There are corresponding relations between operators of quantum systems and corresponding physical quantities of classical systems, such as momentum, energy and Hamiltonian, so Schrdinger equation models of corresponding quantum control systems via quantization could been obtained from classical control systems, and then establish formal state space models through the suitable transformation from Schrdinger equations for these quantum control systems. This method provides a new kind of path for modeling in quantum control.
文摘作为机器学习领域的研究新方向,多无源域适应旨在将多个源域模型中的知识迁移到目标域,以实现对目标域样本的准确预测。本质上,解决多无源域适应的关键在于如何量化多个源模型对目标域的贡献,并利用源模型中的多样性知识来适应目标域。为了应对上述问题,提出了一种基于源模型贡献量化(Source Model Contribution Quantizing,SMCQ)的多无源域适应方法。具体而言,提出了源模型可转移性感知,以量化源模型的可转移性贡献,从而为目标域模型有效地分配源模型的自适应权重。其次,引入了信息最大化方法,以缩小跨域的分布差异,并解决模型退化的问题。然后,提出了可信划分全局对齐方法,该方法用于划分高可信和低可信样本,以应对域差异引起的嘈杂环境,并有效降低标签分配错误的风险。此外,还引入了样本局部一致性损失,以减小伪标签噪声对低可信样本聚类错误的影响。最后,在多个数据集上进行实验,验证了所提方法的有效性。
文摘为快速、方便、正确地将卷积神经网络部署于嵌入式平台实现硬件加速,并解决在硬件部署时遇到的模型计算量大、占用存储多、部署困难等问题,提出一种基于ResNet模型的通道剪枝结合混合精度量化的方法,将模型压缩后,部署于神经网络处理器(neural processing unit, NPU)实现硬件加速。在传统的模型剪枝和量化基础上,采用通道剪枝结合混合精度量化的方法,在保证模型性能的前提下最大程度压缩网络模型。硬件部署推理实验结果表明,该方法可实现对原始模型压缩7.75倍,模型推理速度提升2.55倍,实验验证了该方法对ResNet模型的压缩和硬件推理加速具有一定效果。
文摘In this paper, a new amplitude quantization synthesis method for ultralow sidelobe phased arrays is proposed, which is based on the constrained nonlinear optimization algorithm. By introducing a set of critical constraint conditions into the optimization model, we can directly quantize the amplitude distribution instead of replacing it with a continuous equivalent aperture antenna. The mutual coupling and the element patterns are also considered in the quantization synthesis. Finally, some array simulation results are given to show the effectiveness of the method.
文摘随着人工智能的发展,深度神经网络成为多种模式识别任务中必不可少的工具,由于深度卷积神经网络(CNN)参数量巨大、计算复杂度高,将它部署到计算资源和存储空间受限的边缘计算设备上成为一项挑战。因此,深度网络压缩成为近年来的研究热点。低秩分解与向量量化是深度网络压缩中重要的两个研究分支,其核心思想都是通过找到原网络结构的一种紧凑型表达,从而降低网络参数的冗余程度。通过建立联合压缩框架,提出一种基于低秩分解和向量量化的深度网络压缩方法——可量化的张量分解(QTD)。该方法能够在网络低秩结构的基础上实现进一步的量化,从而得到更大的压缩比。在CIFAR-10数据集上对经典ResNet和该方法进行验证的实验结果表明,QTD能够在准确率仅损失1.71个百分点的情况下,将网络参数量压缩至原来的1%。而在大型数据集ImageNet上把所提方法与基于量化的方法PQF(Permute,Quantize,and Fine-tune)、基于低秩分解的方法TDNR(Tucker Decomposition with Nonlinear Response)和基于剪枝的方法CLIP-Q(Compression Learning by In-parallel Pruning-Quantization)进行比较与分析的实验结果表明,QTD能够在相同压缩范围下实现更好的分类准确率。
