One of the challenges currently facing the quantum computing community is the design of quantum circuits which can efficiently run on near-term quantum computers, known as the quantum compiling problem. Algorithms such as the Variational Quantum Eigensolver (VQE), Quantum Approximate Optimization Algorithm (QAOA), and Quantum Architecture Search (QAS) have been shown to generate or find optimal near-term quantum circuits. However, these methods are computationally expensive and yield little insight into the circuit design process. In this paper, we propose Quantum Deep Dreaming (QDD), an algorithm that generates optimal quantum circuit architectures for specified objectives, such as ground state preparation, while providing insight into the circuit design process. In QDD, we first train a neural network to predict some property of a quantum circuit (such as VQE energy). Then, we employ the Deep Dreaming technique on the trained network to iteratively update an initial circuit to achieve a target property value (such as ground state VQE energy). Importantly, this iterative updating allows us to analyze the intermediate circuits of the dreaming process and gain insights into the circuit features that the network is modifying during dreaming. We demonstrate that QDD successfully generates, or 'dreams', circuits of six qubits close to ground state energy (Transverse Field Ising Model VQE energy) and that dreaming analysis yields circuit design insights. QDD is designed to optimize circuits with any target property and can be applied to circuit design problems both within and outside of quantum chemistry. Hence, QDD lays the foundation for the future discovery of optimized quantum circuits and for increased interpretability of automated quantum algorithm design.
translated by 谷歌翻译
迄今为止,迄今为止,众所周知,对广泛的互补临床相关任务进行了全面比较了医学图像登记方法。这限制了采用研究进展,以防止竞争方法的公平基准。在过去五年内已经探讨了许多新的学习方法,但优化,建筑或度量战略的问题非常适合仍然是开放的。 Learn2reg涵盖了广泛的解剖学:脑,腹部和胸部,方式:超声波,CT,MRI,群体:患者内部和患者内部和监督水平。我们为3D注册的培训和验证建立了较低的入境障碍,这帮助我们从20多个独特的团队中汇编了65多个单独的方法提交的结果。我们的互补度量集,包括稳健性,准确性,合理性和速度,使得能够独特地位了解当前的医学图像登记现状。进一步分析监督问题的转移性,偏见和重要性,主要是基于深度学习的方法的优越性,并将新的研究方向开放到利用GPU加速的常规优化的混合方法。
translated by 谷歌翻译
数字病理学的最新进展导致了对通过活检图像的数据库搜索的组织病理学图像检索(HIR)系统,以找到与给定查询图像的类似情况。这些HIR系统允许病理学家毫不费力地和有效地访问数千个先前诊断的病例,以便利用相应的病理报告中的知识。由于HIR系统可能需要处理数百万千兆像素图像,因此必须使用紧凑型图像特征的提取以允许有效准确的检索。在本文中,我们提出了克条形码的应用作为HIR系统的图像特征。与大多数特征生成方案不同,Gram条形码基于高阶统计,通过总结卷积神经网络层中的不同特征图之间的相关性来描述组织纹理。我们使用预先训练的VGG19网络在三个公共数据集中运行HIR实验,用于Gram条形码生成,展示高度竞争的结果。
translated by 谷歌翻译
通常用于深度学习的陡峭血液算法,使用梯度作为下降方向,或者在使用预处理方向偏移之后。在许多场景中,计算梯度由于复杂或非可微分的成本函数而具有数值困难,特别是奇异点旁边。在这项工作中,我们专注于常见于无监督成本职能的总变化半规范的推导。具体而言,我们在新颖的迭代方案中推导出对硬L1平滑度约束的可分辨率代理,我们称之为成本展开。在培训期间产生更准确的梯度,我们的方法通过改进的收敛来实现给定DNN模型的更精细预测,而无需修改其架构或增加计算复杂性。我们在无监督的光学流任务中展示了我们的方法。在培训众所周知的基线训练期间,更换L1平滑度限制,我们报告了对MPI Sintel和Kitti 2015无监督的光学流量基准的改进结果。特别是,我们报告EPE在封闭像素上减少了高达15.82%的,其中平滑度约束是显性的,使得能够检测更加清晰的运动边缘。
translated by 谷歌翻译