Polypharmacy, most often defined as the simultaneous consumption of five or more drugs at once, is a prevalent phenomenon in the older population. Some of these polypharmacies, deemed inappropriate, may be associated with adverse health outcomes such as death or hospitalization. Considering the combinatorial nature of the problem as well as the size of claims database and the cost to compute an exact association measure for a given drug combination, it is impossible to investigate every possible combination of drugs. Therefore, we propose to optimize the search for potentially inappropriate polypharmacies (PIPs). To this end, we propose the OptimNeuralTS strategy, based on Neural Thompson Sampling and differential evolution, to efficiently mine claims datasets and build a predictive model of the association between drug combinations and health outcomes. We benchmark our method using two datasets generated by an internally developed simulator of polypharmacy data containing 500 drugs and 100 000 distinct combinations. Empirically, our method can detect up to 33\% of PIPs while maintaining an average precision score of 99\% using 10 000 time steps.

Remote sensing of the Earth's surface water is critical in a wide range of environmental studies, from evaluating the societal impacts of seasonal droughts and floods to the large-scale implications of climate change. Consequently, a large literature exists on the classification of water from satellite imagery. Yet, previous methods have been limited by 1) the spatial resolution of public satellite imagery, 2) classification schemes that operate at the pixel level, and 3) the need for multiple spectral bands. We advance the state-of-the-art by 1) using commercial imagery with panchromatic and multispectral resolutions of 30 cm and 1.2 m, respectively, 2) developing multiple fully convolutional neural networks (FCN) that can learn the morphological features of water bodies in addition to their spectral properties, and 3) FCN that can classify water even from panchromatic imagery. This study focuses on rivers in the Arctic, using images from the Quickbird, WorldView, and GeoEye satellites. Because no training data are available at such high resolutions, we construct those manually. First, we use the RGB, and NIR bands of the 8-band multispectral sensors. Those trained models all achieve excellent precision and recall over 90% on validation data, aided by on-the-fly preprocessing of the training data specific to satellite imagery. In a novel approach, we then use results from the multispectral model to generate training data for FCN that only require panchromatic imagery, of which considerably more is available. Despite the smaller feature space, these models still achieve a precision and recall of over 85%. We provide our open-source codes and trained model parameters to the remote sensing community, which paves the way to a wide range of environmental hydrology applications at vastly superior accuracies and 2 orders of magnitude higher spatial resolution than previously possible.

The most useful data mining primitives are distance measures. With an effective distance measure, it is possible to perform classification, clustering, anomaly detection, segmentation, etc. For single-event time series Euclidean Distance and Dynamic Time Warping distance are known to be extremely effective. However, for time series containing cyclical behaviors, the semantic meaningfulness of such comparisons is less clear. For example, on two separate days the telemetry from an athlete workout routine might be very similar. The second day may change the order in of performing push-ups and squats, adding repetitions of pull-ups, or completely omitting dumbbell curls. Any of these minor changes would defeat existing time series distance measures. Some bag-of-features methods have been proposed to address this problem, but we argue that in many cases, similarity is intimately tied to the shapes of subsequences within these longer time series. In such cases, summative features will lack discrimination ability. In this work we introduce PRCIS, which stands for Pattern Representation Comparison in Series. PRCIS is a distance measure for long time series, which exploits recent progress in our ability to summarize time series with dictionaries. We will demonstrate the utility of our ideas on diverse tasks and datasets.

Like fingerprints, cortical folding patterns are unique to each brain even though they follow a general species-specific organization. Some folding patterns have been linked with neurodevelopmental disorders. However, due to the high inter-individual variability, the identification of rare folding patterns that could become biomarkers remains a very complex task. This paper proposes a novel unsupervised deep learning approach to identify rare folding patterns and assess the degree of deviations that can be detected. To this end, we preprocess the brain MR images to focus the learning on the folding morphology and train a beta-VAE to model the inter-individual variability of the folding. We compare the detection power of the latent space and of the reconstruction errors, using synthetic benchmarks and one actual rare configuration related to the central sulcus. Finally, we assess the generalization of our method on a developmental anomaly located in another region. Our results suggest that this method enables encoding relevant folding characteristics that can be enlightened and better interpreted based on the generative power of the beta-VAE. The latent space and the reconstruction errors bring complementary information and enable the identification of rare patterns of different nature. This method generalizes well to a different region on another dataset. Code is available at https://github.com/neurospin-projects/2022_lguillon_rare_folding_detection.

Transformers have become central to recent advances in computer vision. However, training a vision Transformer (ViT) model from scratch can be resource intensive and time consuming. In this paper, we aim to explore approaches to reduce the training costs of ViT models. We introduce some algorithmic improvements to enable training a ViT model from scratch with limited hardware (1 GPU) and time (24 hours) resources. First, we propose an efficient approach to add locality to the ViT architecture. Second, we develop a new image size curriculum learning strategy, which allows to reduce the number of patches extracted from each image at the beginning of the training. Finally, we propose a new variant of the popular ImageNet1k benchmark by adding hardware and time constraints. We evaluate our contributions on this benchmark, and show they can significantly improve performances given the proposed training budget. We will share the code in https://github.com/BorealisAI/efficient-vit-training.

当网络条件恶化时，视频会议系统的用户体验差，因为当前的视频编解码器根本无法在极低的比特率下运行。最近，已经提出了几种神经替代方案，可以使用每个框架的稀疏表示，例如面部地标信息，以非常低的比特率重建说话的头视频。但是，这些方法在通话过程中具有重大运动或遮挡的情况下会产生不良的重建，并且不会扩展到更高的分辨率。我们设计了Gemino，这是一种基于新型高频条件超分辨率管道的新型神经压缩系统，用于视频会议。 Gemino根据从单个高分辨率参考图像中提取的信息来增强高频细节（例如，皮肤纹理，头发等），为每个目标框架的一个非常低分辨率的版本（例如，皮肤纹理，头发等）。我们使用多尺度体系结构，该体系结构在不同的分辨率下运行模型的不同组件，从而使其扩展到可与720p相当的分辨率，并且我们个性化模型以学习每个人的特定细节，在低比特率上实现了更好的保真度。我们在AIORTC上实施了Gemino，这是WEBRTC的开源Python实现，并表明它在A100 GPU上实时在1024x1024视频上运行，比比特率的比特率低于传统的视频Codecs，以相同的感知质量。

解决了与人类偏好的安全一致性以及学习效率之类的各种目的，越来越多的强化学习研究集中在依赖整个收益分配的风险功能上。关于\ emph {Oplicy风险评估}（OPRA）的最新工作，针对上下文匪徒引入了目标策略的收益率以及有限样本保证的一致估计量，并保证了（并同时保留所有风险）。在本文中，我们将OPRA提升到马尔可夫决策过程（MDPS），其中重要性采样（IS）CDF估计量由于有效样本量较小而遭受较长轨迹的较大差异。为了减轻这些问题，我们合并了基于模型的估计，以开发MDPS回报的CDF的第一个双重鲁棒（DR）估计器。该估计器的差异明显较小，并且在指定模型时，可以实现Cramer-Rao方差下限。此外，对于许多风险功能，下游估计值同时享有较低的偏差和较低的差异。此外，我们得出了非政策CDF和风险估计的第一个Minimax下限，这与我们的误差界限到恒定因子。最后，我们在几种不同的环境上实验表明了DR CDF估计的精度。

我们通过查看在弥漫表面上铸造的对象的阴影来研究个体的生物特征识别信息的问题。我们表明，通过最大似然分析，在代表性的情况下，阴影中的生物特征信息泄漏可以足够用于可靠的身份推断。然后，我们开发了一种基于学习的方法，该方法在实际设置中证明了这种现象，从而利用阴影中的微妙提示是泄漏的来源，而无需任何标记的真实数据。特别是，我们的方法依赖于构建由从每个身份的单个照片获得的3D面模型组成的合成场景。我们以完全无监督的方式将我们从合成数据中学到的知识转移到真实数据中。我们的模型能够很好地概括到真实的域，并且在场景中的几种变体都有坚固的范围。我们报告在具有未知几何形状和遮挡对象的场景中发生的身份分类任务中的高分类精度。

这项研究的目的是评估历史匹配的潜力（HM），以调整具有多尺度动力学的气候系统。通过考虑玩具气候模型，即两尺度的Lorenz96模型并在完美模型设置中生产实验，我们详细探讨了如何需要仔细测试几种内置选择。我们还展示了在参数范围内引入物理专业知识的重要性，这是运行HM的先验性。最后，我们重新审视气候模型调整中的经典过程，该程序包括分别调整慢速和快速组件。通过在Lorenz96模型中这样做，我们说明了合理参数的非唯一性，并突出了从耦合中出现的指标的特异性。本文也有助于弥合不确定性量化，机器学习和气候建模的社区，这是通过在每个社区使用的术语之间建立相同概念的术语并提出有希望的合作途径，从而使气候建模研究受益。

人类的感知可靠地识别3D场景的可移动和不可移动的部分，并通过不完整的观测来完成对象和背景的3D结构。我们不是通过标记的示例来学习此技能，而只是通过观察对象移动来学习。在这项工作中，我们提出了一种方法，该方法在训练时间观察未标记的多视图视频，并学会绘制对复杂场景的单个图像观察，例如带有汽车的街道，将其绘制为3D神经场景表示，该表演将其分解为可移动和可移动和不可移动的零件，同时合理地完成其3D结构。我们通过2D神经地面计划分别参数可移动和不可移动的场景部分。这些地面计划是与接地平面对齐的2D网格，可以将其局部解码为3D神经辐射场。我们的模型通过神经渲染受过训练的自我监督。我们证明，使用简单的启发式方法，例如提取对象以对象的3D表示，新颖的视图合成，实例段和3D边界框预测，预测，预测，诸如提取以对象为中心的3D表示，诸如提取街道规模的3D场景中的各种下游任务可以实现各种下游任务。强调其作为数据效率3D场景理解模型的骨干的价值。这种分离进一步通过对象操纵（例如删除，插入和刚体运动）进行了现场编辑。