Associazione Medici Diabetologi（AMD）收集并管理着全球最大的糖尿病患者记录集合之一，也称为AMD数据库。本文介绍了一个正在进行的项目的初步结果，该项目的重点是人工智能和机器学习技术的应用，以概念化，清洁和分析如此重要且有价值的数据集，目的是提供预测性见解，以更好地支持糖尿病学家的诊断糖尿病学家和治疗选择。

Computational units in artificial neural networks follow a simplified model of biological neurons. In the biological model, the output signal of a neuron runs down the axon, splits following the many branches at its end, and passes identically to all the downward neurons of the network. Each of the downward neurons will use their copy of this signal as one of many inputs dendrites, integrate them all and fire an output, if above some threshold. In the artificial neural network, this translates to the fact that the nonlinear filtering of the signal is performed in the upward neuron, meaning that in practice the same activation is shared between all the downward neurons that use that signal as their input. Dendrites thus play a passive role. We propose a slightly more complex model for the biological neuron, where dendrites play an active role: the activation in the output of the upward neuron becomes optional, and instead the signals going through each dendrite undergo independent nonlinear filterings, before the linear combination. We implement this new model into a ReLU computational unit and discuss its biological plausibility. We compare this new computational unit with the standard one and describe it from a geometrical point of view. We provide a Keras implementation of this unit into fully connected and convolutional layers and estimate their FLOPs and weights change. We then use these layers in ResNet architectures on CIFAR-10, CIFAR-100, Imagenette, and Imagewoof, obtaining performance improvements over standard ResNets up to 1.73%. Finally, we prove a universal representation theorem for continuous functions on compact sets and show that this new unit has more representational power than its standard counterpart.

The paper addresses the problem of time offset synchronization in the presence of temperature variations, which lead to a non-Gaussian environment. In this context, regular Kalman filtering reveals to be suboptimal. A functional optimization approach is developed in order to approximate optimal estimation of the clock offset between master and slave. A numerical approximation is provided to this aim, based on regular neural network training. Other heuristics are provided as well, based on spline regression. An extensive performance evaluation highlights the benefits of the proposed techniques, which can be easily generalized to several clock synchronization protocols and operating environments.

The paper addresses state estimation for clock synchronization in the presence of factors affecting the quality of synchronization. Examples are temperature variations and delay asymmetry. These working conditions make synchronization a challenging problem in many wireless environments, such as Wireless Sensor Networks or WiFi. Dynamic state estimation is investigated as it is essential to overcome non-stationary noises. The two-way timing message exchange synchronization protocol has been taken as a reference. No a-priori assumptions are made on the stochastic environments and no temperature measurement is executed. The algorithms are unequivocally specified offline, without the need of tuning some parameters in dependence of the working conditions. The presented approach reveals to be robust to a large set of temperature variations, different delay distributions and levels of asymmetry in the transmission path.

Image super-resolution is a common task on mobile and IoT devices, where one often needs to upscale and enhance low-resolution images and video frames. While numerous solutions have been proposed for this problem in the past, they are usually not compatible with low-power mobile NPUs having many computational and memory constraints. In this Mobile AI challenge, we address this problem and propose the participants to design an efficient quantized image super-resolution solution that can demonstrate a real-time performance on mobile NPUs. The participants were provided with the DIV2K dataset and trained INT8 models to do a high-quality 3X image upscaling. The runtime of all models was evaluated on the Synaptics VS680 Smart Home board with a dedicated edge NPU capable of accelerating quantized neural networks. All proposed solutions are fully compatible with the above NPU, demonstrating an up to 60 FPS rate when reconstructing Full HD resolution images. A detailed description of all models developed in the challenge is provided in this paper.

Feature selection is of great importance in Machine Learning, where it can be used to reduce the dimensionality of classification, ranking and prediction problems. The removal of redundant and noisy features can improve both the accuracy and scalability of the trained models. However, feature selection is a computationally expensive task with a solution space that grows combinatorically. In this work, we consider in particular a quadratic feature selection problem that can be tackled with the Quantum Approximate Optimization Algorithm (QAOA), already employed in combinatorial optimization. First we represent the feature selection problem with the QUBO formulation, which is then mapped to an Ising spin Hamiltonian. Then we apply QAOA with the goal of finding the ground state of this Hamiltonian, which corresponds to the optimal selection of features. In our experiments, we consider seven different real-world datasets with dimensionality up to 21 and run QAOA on both a quantum simulator and, for small datasets, the 7-qubit IBM (ibm-perth) quantum computer. We use the set of selected features to train a classification model and evaluate its accuracy. Our analysis shows that it is possible to tackle the feature selection problem with QAOA and that currently available quantum devices can be used effectively. Future studies could test a wider range of classification models as well as improve the effectiveness of QAOA by exploring better performing optimizers for its classical step.

这项工作提出了专门针对粒子探测器的低潜伏期图神经网络（GNN）设计的新型可重构体系结构。加速粒子探测器的GNN是具有挑战性的，因为它需要次微秒延迟才能在CERN大型强子撞机实验的级别1触发器中部署网络以进行在线事件选择。本文提出了一种自定义代码转换，并在基于互动网络的GNN中使用完全连接的图表中的矩阵乘法操作降低了强度，从而避免了昂贵的乘法。它利用了稀疏模式以及二进制邻接矩阵，并避免了不规则的内存访问，从而降低了延迟和硬件效率的提高。此外，我们引入了一种基于外部产品的基质乘法方法，该方法通过降低潜伏期设计的强度降低来增强。此外，引入了融合步骤，以进一步降低设计延迟。此外，提出了GNN特异性算法 - 硬件共同设计方法，该方法不仅找到了具有更好延迟的设计，而且在给定的延迟约束下发现了高精度的设计。最后，已经设计和开源了此低延迟GNN硬件体系结构的可自定义模板，该模板可以使用高级合成工具来生成低延迟的FPGA设计，并有效地利用资源。评估结果表明，我们的FPGA实施速度高24倍，并且消耗的功率比GPU实施少45倍。与我们以前的FPGA实施相比，这项工作的延迟降低了6.51至16.7倍。此外，我们的FPGA设计的延迟足以使GNN在亚微秒，实时撞机触发器系统中部署，从而使其能够从提高的精度中受益。

在线社交网络由于其在低质量信息的传播中的作用而积极参与删除恶意社交机器人。但是，大多数现有的机器人检测器都是监督分类器，无法捕获复杂机器人的不断发展的行为。在这里，我们提出了Mulbot，这是一种基于多元时间序列（MTS）的无监督的机器人检测器。我们第一次利用从用户时间表中提取的多维时间功能。我们使用LSTM AutoCododer管理多维性，该模块将MTS投射在合适的潜在空间中。然后，我们对此编码表示形式执行聚类步骤，以识别非常相似用户的密集组 - 一种已知的自动化迹象。最后，我们执行一项二进制分类任务，以达到F1得分$ = 0.99 $，表现优于最先进的方法（F1分数$ \ le 0.97 $）。 Mulbot不仅在二进制分类任务中取得了出色的成果，而且我们还在一项新颖且实际上相关的任务中证明了它的优势：检测和分离不同的僵尸网络。在此多级分类任务中，我们实现了F1得分$ = 0.96 $。我们通过估计模型中使用的不同特征的重要性，并通过评估Mulbot推广到新看不见的机器人的能力，从而提出了解决监督机器人探测器的概括性缺陷的解决方案。

在本文中，我们将深度学习文献与非线性因素模型联系起来，并表明深度学习估计可以大大改善非线性加性因子模型文献。我们通过扩展Schmidt-Hieber（2020）定理来提供预期风险的界限，并表明这些上限在一组多个响应变量上是均匀的。我们表明，我们的风险界限并不取决于因素的数量。为了构建资产回报的协方差矩阵估计器，我们开发了深层神经网络中误差协方差矩阵的新型数据依赖性估计器。估算器是指灵活的自适应阈值技术，对创新中的异常值很强。我们证明估计量在光谱规范中是一致的。然后使用该结果，我们显示了协方差矩阵的一致性和收敛速率和资产回报的精确矩阵估计器。两种结果中的收敛速度并不取决于因素的数量，因此我们的收敛性是因子模型文献中的一个新结果，因为这一事实是因素的数量妨碍了更好的估计和预测。除了精确矩阵结果外，即使资产数量大于时间跨度，我们也可以获得我们所有的结果，并且两个数量都在增长。各种蒙特卡洛模拟证实了我们的大型样本发现，并揭示了DNN-FM的卓越精确度，以估计连接因子和可观察变量的真实潜在功能形式，以及与竞争方法相比的协方差和精确矩阵。此外，在大多数情况下，就样本外投资组合策略而言，在样本外预测应用程序中，就样本外投资组合标准偏差和Sharpe比率而言，它的表现优于其他投资组合策略。

现代的天空调查正在产生大量的观测数据，这使经典方法的应用用于分类和分析对象具有挑战性和耗时的。但是，使用自动机器和深度学习方法可能会大大减轻此问题。我们提出了一种新的深度学习工具Ulisse，它从单个原型对象开始，能够识别具有相同形态和光度特性的对象，因此可以创建候选苏西亚列表。在这项工作中，我们专注于在斯隆数字天空调查的星系样本中应用方法来检测AGN候选物，因为光带中主动银河系核（AGN）的鉴定和分类仍然是外层术天文学的挑战性任务。乌里斯（Ulisse）旨在初步探索大型天空调查，直接使用从图像网数据集提取的功能来执行相似性搜索。该方法能够快速识别仅从给定原型的单个图像开始的候选人列表，而无需任何耗时的神经网络训练。我们的实验表明，乌里斯（Ulisse）能够根据宿主星系形态，颜色和中央核源的存在的结合来鉴定AGN候选物，检索效率从21％到65％（包括复合源）（包括复合源），这是基于宿主的候选者。随机猜测基线为12％。我们发现，与具有螺旋形或晚期特性的原型相反，Ulisse在早期型宿主星系中检索AGN最有效。根据这项工作中描述的结果，Ulisse可以是在当前和未来的广阔田野调查（例如欧几里得，LSST等）中选择不同类型的天体物理对象的有前途的工具，该工具每晚都针对数百万个来源。