由能够连接和交换消息的越来越多的移动设备而激励，我们提出了一种旨在模拟和分析网络中节点移动性的方法。我们注意到文献中的许多现有解决方案依赖于直接在节点联系人图表上计算的拓扑测量，旨在捕获节点在有利于原型设计，设计和部署移动网络的连接和移动模式方面的重要性。但是，每个措施都具有其特异性，并且无法概括最终随时间变化的节点重要性概念。与以前的方法不同，我们的方法基于节点嵌入方法，该方法模型和推出在保留其空间和时间特征的同时在移动性和连接模式中对节点的重要性。我们专注于基于一丝小组会议的案例研究。结果表明，我们的方法提供了提取不同移动性和连接模式的丰富表示，这可能有助于移动网络中的各种应用和服务。
translated by 谷歌翻译
We describe a Physics-Informed Neural Network (PINN) that simulates the flow induced by the astronomical tide in a synthetic port channel, with dimensions based on the Santos - S\~ao Vicente - Bertioga Estuarine System. PINN models aim to combine the knowledge of physical systems and data-driven machine learning models. This is done by training a neural network to minimize the residuals of the governing equations in sample points. In this work, our flow is governed by the Navier-Stokes equations with some approximations. There are two main novelties in this paper. First, we design our model to assume that the flow is periodic in time, which is not feasible in conventional simulation methods. Second, we evaluate the benefit of resampling the function evaluation points during training, which has a near zero computational cost and has been verified to improve the final model, especially for small batch sizes. Finally, we discuss some limitations of the approximations used in the Navier-Stokes equations regarding the modeling of turbulence and how it interacts with PINNs.
translated by 谷歌翻译
Despite being responsible for state-of-the-art results in several computer vision and natural language processing tasks, neural networks have faced harsh criticism due to some of their current shortcomings. One of them is that neural networks are correlation machines prone to model biases within the data instead of focusing on actual useful causal relationships. This problem is particularly serious in application domains affected by aspects such as race, gender, and age. To prevent models from incurring on unfair decision-making, the AI community has concentrated efforts in correcting algorithmic biases, giving rise to the research area now widely known as fairness in AI. In this survey paper, we provide an in-depth overview of the main debiasing methods for fairness-aware neural networks in the context of vision and language research. We propose a novel taxonomy to better organize the literature on debiasing methods for fairness, and we discuss the current challenges, trends, and important future work directions for the interested researcher and practitioner.
translated by 谷歌翻译
End-to-end deep neural networks (DNNs) have become state-of-the-art (SOTA) for solving inverse problems. Despite their outstanding performance, during deployment, such networks are sensitive to minor variations in the training pipeline and often fail to reconstruct small but important details, a feature critical in medical imaging, astronomy, or defence. Such instabilities in DNNs can be explained by the fact that they ignore the forward measurement model during deployment, and thus fail to enforce consistency between their output and the input measurements. To overcome this, we propose a framework that transforms any DNN for inverse problems into a measurement-consistent one. This is done by appending to it an implicit layer (or deep equilibrium network) designed to solve a model-based optimization problem. The implicit layer consists of a shallow learnable network that can be integrated into the end-to-end training. Experiments on single-image super-resolution show that the proposed framework leads to significant improvements in reconstruction quality and robustness over the SOTA DNNs.
translated by 谷歌翻译
The International Atomic Energy Agency (IAEA) stopping power database is a highly valued public resource compiling most of the experimental measurements published over nearly a century. The database-accessible to the global scientific community-is continuously updated and has been extensively employed in theoretical and experimental research for more than 30 years. This work aims to employ machine learning algorithms on the 2021 IAEA database to predict accurate electronic stopping power cross sections for any ion and target combination in a wide range of incident energies. Unsupervised machine learning methods are applied to clean the database in an automated manner. These techniques purge the data by removing suspicious outliers and old isolated values. A large portion of the remaining data is used to train a deep neural network, while the rest is set aside, constituting the test set. The present work considers collisional systems only with atomic targets. The first version of the ESPNN (electronic stopping power neural-network code), openly available to users, is shown to yield predicted values in excellent agreement with the experimental results of the test set.
translated by 谷歌翻译
在机器学习中，对神经网络集合（NNE）（NNE）引起了新的兴趣，从而从一组较小的模型（而不是从单个较大的模型）中获得了预测作为汇总的预测。在这里，我们展示了如何使用随机系统中稀有轨迹的技术来定义和训练NNE。我们根据模型参数的轨迹定义一个NNE，在简单的，离散的时间，扩散动力学下，并通过将这些轨迹偏向较小的时间整合损失来训练NNE，并由适当的计数领域控制，这些领域的作用是超参数。我们证明了该技术在一系列简单监督的学习任务上的生存能力。与更常规的基于梯度的方法相比，我们讨论了轨迹采样方法的潜在优势。
translated by 谷歌翻译
我们介绍了IST和Unmabel对WMT 2022关于质量估计（QE）的共享任务的共同贡献。我们的团队参与了所有三个子任务：（i）句子和单词级质量预测；（ii）可解释的量化宽松；（iii）关键错误检测。对于所有任务，我们在彗星框架之上构建，将其与OpenKIWI的预测估计架构连接，并为其配备单词级序列标记器和解释提取器。我们的结果表明，在预处理过程中合并参考可以改善下游任务上多种语言对的性能，并且通过句子和单词级别的目标共同培训可以进一步提高。此外，将注意力和梯度信息结合在一起被证明是提取句子级量化量化宽松模型的良好解释的首要策略。总体而言，我们的意见书在几乎所有语言对的所有三个任务中都取得了最佳的结果。
translated by 谷歌翻译
关于使用ML模型的一个基本问题涉及其对提高决策透明度的预测的解释。尽管已经出现了几种可解释性方法，但已经确定了有关其解释可靠性的一些差距。例如，大多数方法都是不稳定的（这意味着它们在数据中提供了截然不同的解释），并且不能很好地应对无关的功能（即与标签无关的功能）。本文介绍了两种新的可解释性方法，即Varimp和Supclus，它们通过使用局部回归拟合的加权距离来克服这些问题，以考虑可变重要性。 Varimp生成了每个实例的解释，可以应用于具有更复杂关系的数据集，而Supclus解释了具有类似说明的实例集群，并且可以应用于可以找到群集的较简单数据集。我们将我们的方法与最先进的方法进行了比较，并表明它可以根据几个指标产生更好的解释，尤其是在具有无关特征的高维问题中，以及特征与目标之间的关系是非线性的。
translated by 谷歌翻译
我们研究了数据驱动的深度学习方法的潜力，即从观察它们的混合物中分离两个通信信号。特别是，我们假设一个信号之一的生成过程（称为感兴趣的信号（SOI）），并且对第二个信号的生成过程不了解，称为干扰。单通道源分离问题的这种形式也称为干扰拒绝。我们表明，捕获高分辨率的时间结构（非平稳性），可以准确地同步与SOI和干扰，从而带来了可观的性能增长。有了这个关键的见解，我们提出了一种域信息神经网络（NN）设计，该设计能够改善“现成” NNS和经典检测和干扰拒绝方法，如我们的模拟中所示。我们的发现突出了特定于交流领域知识的关键作用在开发数据驱动的方法方面发挥了作用，这些方法具有前所未有的收益的希望。
translated by 谷歌翻译
ICECUBE是一种用于检测1 GEV和1 PEV之间大气和天体中微子的光学传感器的立方公斤阵列，该阵列已部署1.45 km至2.45 km的南极的冰盖表面以下1.45 km至2.45 km。来自ICE探测器的事件的分类和重建在ICeCube数据分析中起着核心作用。重建和分类事件是一个挑战，这是由于探测器的几何形状，不均匀的散射和冰中光的吸收，并且低于100 GEV的光，每个事件产生的信号光子数量相对较少。为了应对这一挑战，可以将ICECUBE事件表示为点云图形，并将图形神经网络（GNN）作为分类和重建方法。 GNN能够将中微子事件与宇宙射线背景区分开，对不同的中微子事件类型进行分类，并重建沉积的能量，方向和相互作用顶点。基于仿真，我们提供了1-100 GEV能量范围的比较与当前ICECUBE分析中使用的当前最新最大似然技术，包括已知系统不确定性的影响。对于中微子事件分类，与当前的IceCube方法相比，GNN以固定的假阳性速率（FPR）提高了信号效率的18％。另外，GNN在固定信号效率下将FPR的降低超过8（低于半百分比）。对于能源，方向和相互作用顶点的重建，与当前最大似然技术相比，分辨率平均提高了13％-20％。当在GPU上运行时，GNN能够以几乎是2.7 kHz的中位数ICECUBE触发速率的速率处理ICECUBE事件，这打开了在在线搜索瞬态事件中使用低能量中微子的可能性。
translated by 谷歌翻译