现代机器学习模型使用大型数据集使用越来越多的参数(GPT-3参数1750亿参数),以获得更好的性能。更大的是常态。光学计算已被恢复为通过执行线性操作的同时降低电力的光学加速器的大规模计算的潜在解决方案。但是,要用光实现有效的计算,在光学上而不是电子上创建和控制非线性仍然是一个挑战。这项研究探讨了一种储层计算方法(RC)方法,通过该方法,在绝缘体上的Linbo3中的14毫米长的几种模式波导被用作复杂的非线性光学处理器。数据集在飞秒脉冲的频谱上进行数字编码,然后在波导中启动。输出频谱非线性取决于输入。我们通过实验表明,与非转换数据相比,使用波导的输出谱提高了几个数据库的分类精度,使用来自波导的输出频谱具有784个参数的简单数字线性分类器,约为10 $ \%$。相比之下,必须具有40000个参数的深数字神经网络(NN)才能达到相同的准确性。将参数的数量减少$ \ sim $ 50,这说明了紧凑的光RC方法可以与深数字NN一起执行。
translated by 谷歌翻译
我们提出了一个具有物理信息的神经网络,作为生物样品层析成像重建的正向模型。我们证明,通过用Helmholtz方程训练该网络作为物理损失,我们可以准确预测散射场。可以证明,可以对不同的样本进行微调的验证网络,并用于与其他数值解决方案更快地解决散射问题。我们通过数值和实验结果评估我们的方法。我们的物理知识神经网络可以推广到任何前进和反向散射问题。
translated by 谷歌翻译
光学衍射断层扫描(ODT)是一种新兴的3D成像技术,用于半透明样品的折射率(RI)的3D重建。已经提出了各种逆模型,以基于对不同样品(例如BORN和RYTOV近似)的全息检测来重建3D RI。但是,这种近似通常会遭受所谓的缺失键问题,从而导致沿光轴的最终重建伸长。已经提出了不同的迭代方案,以解决依靠物理前向模型和旨在填充K空间的错误函数的丢失锥问题,从而消除缺失的问题问题并达到更好的重建精度。在本文中,我们提出了一种使用3D神经网络(NN)的不同方法。 NN经过基于光波传播物理的物理模型得出的成本函数训练。 3D NN以3D RI重建(即出生或Rytov)的初始猜测开始,并旨在根据错误函数重建更好的3D重建。通过这种技术,可以对NN进行训练,而无需任何示例,即不适当的重建(出生或Rytov)与地面真相(真实形状)之间的关系。
translated by 谷歌翻译
Pandemic(epidemic) modeling, aiming at disease spreading analysis, has always been a popular research topic especially following the outbreak of COVID-19 in 2019. Some representative models including SIR-based deep learning prediction models have shown satisfactory performance. However, one major drawback for them is that they fall short in their long-term predictive ability. Although graph convolutional networks (GCN) also perform well, their edge representations do not contain complete information and it can lead to biases. Another drawback is that they usually use input features which they are unable to predict. Hence, those models are unable to predict further future. We propose a model that can propagate predictions further into the future and it has better edge representations. In particular, we model the pandemic as a spatial-temporal graph whose edges represent the transition of infections and are learned by our model. We use a two-stream framework that contains GCN and recursive structures (GRU) with an attention mechanism. Our model enables mobility analysis that provides an effective toolbox for public health researchers and policy makers to predict how different lock-down strategies that actively control mobility can influence the spread of pandemics. Experiments show that our model outperforms others in its long-term predictive power. Moreover, we simulate the effects of certain policies and predict their impacts on infection control.
translated by 谷歌翻译
前列腺癌是美国男性癌症死亡的第二大原因。前列腺MRI的诊断通常依赖于准确的前列腺区域分割。但是,最新的自动分割方法通常无法产生前列腺区域的含有良好的体积分割,因为某些切片的前列腺MRI(例如碱基和顶点片)比其他切片更难分割。可以通过考虑相邻切片之间的跨片段关系来克服这一困难,但是当前的方法不能完全学习和利用这种关系。在本文中,我们提出了一种新型的跨板夹心注意机制,我们在变压器模块中使用该机制,以系统地学习不同尺度的跨斜纹关系。该模块可以在任何基于Skip Connections的现有基于学习的细分框架中使用。实验表明,我们的跨板块注意力能够捕获前列腺区域分割中的跨板片信息,并提高当前最新方法的性能。我们的方法提高了外围区域的分割精度,从而使所有前列腺切片(Apex,Mid-Gland和Base)的分割结果保持一致。
translated by 谷歌翻译
从人们到3D面部模型的面部表情转移是一种经典的计算机图形问题。在本文中,我们提出了一种基于学习的基于学习的方法,将来自图像和视频从图像和视频转移到面部头颈络合物的生物力学模型。利用面部动作编码系统(FACS)作为表达空间的中间表示,我们训练深度神经网络,采用FACS动作单元(AUS),并为肌肉骨骼模型输出合适的面部肌肉和钳口激活信号。通过生物力学模拟,激活变形了面部软组织,从而将表达转移到模型。我们的方法具有比以前的方法相比。首先,面部表情是剖贯的一致,因为我们的生物力学模型模拟了面部,头部和颈部的相关解剖结构。其次,通过使用从生物力学模型本身产生的数据训练神经网络,我们消除了数据收集的表达式转移的手动努力。通过涉及转移到面部表情和头部姿势的实验,通过实验证明了我们的方法的成功。
translated by 谷歌翻译
Image segmentation is a key topic in image processing and computer vision with applications such as scene understanding, medical image analysis, robotic perception, video surveillance, augmented reality, and image compression, among many others. Various algorithms for image segmentation have been developed in the literature. Recently, due to the success of deep learning models in a wide range of vision applications, there has been a substantial amount of works aimed at developing image segmentation approaches using deep learning models. In this survey, we provide a comprehensive review of the literature at the time of this writing, covering a broad spectrum of pioneering works for semantic and instance-level segmentation, including fully convolutional pixel-labeling networks, encoder-decoder architectures, multi-scale and pyramid based approaches, recurrent networks, visual attention models, and generative models in adversarial settings. We investigate the similarity, strengths and challenges of these deep learning models, examine the most widely used datasets, report performances, and discuss promising future research directions in this area.
translated by 谷歌翻译