当前的电力和天然气（NG）基础设施的快速转变必须达到中世纪的二氧化碳排放量减少目标。这需要在代表性的需求和供应模式，运营限制和政策注意事项下对联合Power-NG系统进行长期计划。我们的工作是由与解决Power-NG系统联合计划的生成和传输扩展问题（GTEP）相关的计算和实际挑战所激发的。具体而言，我们专注于从相应网络中有效从功率和NG数据中提取一组代表日，并使用此组来减少解决GTEP所需的计算负担。我们为多个时间分辨率能源系统（游戏）提出了一个图形自动编码器，以捕获相互依存网络中的时空需求模式，并说明可用数据的时间分辨率的差异。所得的嵌入在聚类算法中用于选择代表日。我们评估了方法在解决新英格兰联合Power-NG系统校准的GTEP公式方面的有效性。该公式说明了功率和NG系统之间的物理相互依赖性，包括关节排放约束。我们的结果表明，从游戏中获得的代表日的集合不仅使我们能够谨慎地解决GTEP公式，而且还可以实现实施联合计划决策的较低成本。

运输网络中的模态拆分预测有可能支持网络运营商管理交通拥堵和提高运输服务可靠性。我们专注于使用高维旅行时间数据选择一种运输方式而不是另一种运输方式的旅行者的小时预测问题。我们使用逻辑回归作为基本模型，并采用各种正则化技术来进行可变选择，以防止过度拟合和解决多重共线性问题。重要的是，我们解释了模态拆分和旅行者对旅行时间变化的总体反应性的固有变异性的预测准确性结果。通过可视化模型参数，我们得出的结论是，发现对预测精度从每小时到小时的变化很重要，并包括拓扑核心和/或高度拥挤的段。我们将我们的方法应用于旧金山湾区高速公路和快速运输网络，并与预先指定的变量选择方法相比，我们的方法具有卓越的预测准确性和解释性。

Neural Radiance Fields (NeRFs) are emerging as a ubiquitous scene representation that allows for novel view synthesis. Increasingly, NeRFs will be shareable with other people. Before sharing a NeRF, though, it might be desirable to remove personal information or unsightly objects. Such removal is not easily achieved with the current NeRF editing frameworks. We propose a framework to remove objects from a NeRF representation created from an RGB-D sequence. Our NeRF inpainting method leverages recent work in 2D image inpainting and is guided by a user-provided mask. Our algorithm is underpinned by a confidence based view selection procedure. It chooses which of the individual 2D inpainted images to use in the creation of the NeRF, so that the resulting inpainted NeRF is 3D consistent. We show that our method for NeRF editing is effective for synthesizing plausible inpaintings in a multi-view coherent manner. We validate our approach using a new and still-challenging dataset for the task of NeRF inpainting.

Many, if not most, systems of interest in science are naturally described as nonlinear dynamical systems (DS). Empirically, we commonly access these systems through time series measurements, where often we have time series from different types of data modalities simultaneously. For instance, we may have event counts in addition to some continuous signal. While by now there are many powerful machine learning (ML) tools for integrating different data modalities into predictive models, this has rarely been approached so far from the perspective of uncovering the underlying, data-generating DS (aka DS reconstruction). Recently, sparse teacher forcing (TF) has been suggested as an efficient control-theoretic method for dealing with exploding loss gradients when training ML models on chaotic DS. Here we incorporate this idea into a novel recurrent neural network (RNN) training framework for DS reconstruction based on multimodal variational autoencoders (MVAE). The forcing signal for the RNN is generated by the MVAE which integrates different types of simultaneously given time series data into a joint latent code optimal for DS reconstruction. We show that this training method achieves significantly better reconstructions on multimodal datasets generated from chaotic DS benchmarks than various alternative methods.

Mapping with uncertainty representation is required in many research domains, such as localization and sensor fusion. Although there are many uncertainty explorations in pose estimation of an ego-robot with map information, the quality of the reference maps is often neglected. To avoid the potential problems caused by the errors of maps and a lack of the uncertainty quantification, an adequate uncertainty measure for the maps is required. In this paper, uncertain building models with abstract map surface using Gaussian Process (GP) is proposed to measure the map uncertainty in a probabilistic way. To reduce the redundant computation for simple planar objects, extracted facets from a Gaussian Mixture Model (GMM) are combined with the implicit GP map while local GP-block techniques are used as well. The proposed method is evaluated on LiDAR point clouds of city buildings collected by a mobile mapping system. Compared to the performances of other methods such like Octomap, Gaussian Process Occupancy Map (GPOM) and Bayersian Generalized Kernel Inference (BGKOctomap), our method has achieved higher Precision-Recall AUC for evaluated buildings.

The Codex model has demonstrated extraordinary competence in synthesizing code from natural language problem descriptions. However, in order to reveal unknown failure modes and hidden biases, such large-scale models must be systematically subjected to multiple and diverse evaluation studies. In this work, we evaluate the code synthesis capabilities of the Codex model based on a set of 115 Python problem statements from a popular competitive programming portal: HackerRank. Our evaluation shows that Codex is indeed proficient in Python, solving 96% of the problems in a zero-shot setting, and 100% of the problems in a few-shot setting. However, Codex exhibits clear signs of generating memorized code based on our evaluation. This is alarming, especially since the adoption and use of such models could directly impact how code is written and produced in the foreseeable future. With this in mind, we further discuss and highlight some of the prominent risks associated with large-scale models of source code. Finally, we propose a framework for code-synthesis evaluation using variations of problem statements based on mutations.

在许多科学学科中，我们有兴趣推断一组观察到的时间序列的非线性动力学系统，这是面对混乱的行为和噪音，这是一项艰巨的任务。以前的深度学习方法实现了这一目标，通常缺乏解释性和障碍。尤其是，即使基本动力学生存在较低维的多种多样的情况下，忠实嵌入通常需要的高维潜在空间也会阻碍理论分析。在树突计算的新兴原则的推动下，我们通过线性样条基础扩展增强了动态解释和数学可牵引的分段线性（PL）复发性神经网络（RNN）。我们表明，这种方法保留了简单PLRNN的所有理论上吸引人的特性，但在相对较低的尺寸中提高了其近似任意非线性动态系统的能力。我们采用两个框架来训练该系统，一个将反向传播的时间（BPTT）与教师强迫结合在一起，另一个将基于快速可扩展的变异推理的基础。我们表明，树枝状扩展的PLRNN可以在各种动力学系统基准上获得更少的参数和尺寸，并与其他方法进行比较，同时保留了可拖动和可解释的结构。

尽管在整个科学和工程中都无处不在，但只有少数部分微分方程（PDE）具有分析或封闭形式的解决方案。这激发了有关PDE的数值模拟的大量经典工作，最近，对数据驱动技术的研究旋转了机器学习（ML）。最近的一项工作表明，与机器学习的经典数值技术的混合体可以对任何一种方法提供重大改进。在这项工作中，我们表明，在纳入基于物理学的先验时，数值方案的选择至关重要。我们以基于傅立叶的光谱方法为基础，这些光谱方法比其他数值方案要高得多，以模拟使用平滑且周期性解决方案的PDE。具体而言，我们为流体动力学的三个模型PDE开发了ML增强的光谱求解器，从而提高了标准光谱求解器在相同分辨率下的准确性。我们还展示了一些关键设计原则，用于将机器学习和用于解决PDE的数值方法结合使用。

与痴呆症相关的认知障碍（CI）在全球范围内影响超过5500万人，并且每3秒钟以一个新病例的速度迅速增长。随着临床试验反复出现的失败，早期诊断至关重要，但是在低水平和中等收入国家中，全球75％的痴呆症病例未被诊断为90％。众所周知，当前的诊断方法是复杂的，涉及对医学笔记，大量认知测试，昂贵的脑部扫描或脊柱液体测试的手动审查。与CI相关的信息经常在电子健康记录（EHR）中找到，并且可以为早期诊断提供重要线索，但是专家的手动审查是繁琐的，并且容易发生。该项目开发了一种新型的最新自动筛选管道，用于可扩展和高速发现EHR中的CI。为了了解EHR中复杂语言结构的语言环境，构建了一个8,656个序列的数据库，以训练基于注意力的深度学习自然语言处理模型以对序列进行分类。使用序列级别分类器开发了基于逻辑回归的患者级别预测模型。深度学习系统的精度达到了93％，AUC = 0.98，以识别其EHR中没有较早诊断，与痴呆有关的诊断代码或与痴呆有关的药物的患者。否则，这些患者将未被发现或检测到太晚。 EHR筛选管道已部署在Neurahealthnlp中，这是一种用于自动化和实时CI筛选的Web应用程序，只需将EHR上传到浏览器中即可。 Neurahealthnlp更便宜，更快，更容易获得，并且胜过当前的临床方法，包括基于文本的分析和机器学习方法。它使得早期诊断可在稀缺的医疗服务中可行，但可访问的互联网或蜂窝服务。

痴呆症是一种神经退行性疾病，导致认知下降，并影响全世界超过5000万人。痴呆症是由医疗保健专业人士诊断的 - 只有患有痴呆症的四个人中只有一名诊断出来。即使制造诊断，也可能无法作为患者图表中的疾病（ICD）诊断码的结构化国际分类。与认知障碍（CI）有关的信息通常在电子健康记录（EHR）中发现，但专家临床医生票据的手工审查既耗时，往往容易出错。本票据的自动化挖掘为在EHR数据中标记有认知障碍患者的机会。我们开发了自然语言处理（NLP）工具，以识别具有认知障碍的患者，并证明语言背景提高了认知障碍分类任务的性能。我们微调我们的注意力深入学习模型，可以从复杂的语言结构中学习，并且相对于基线NLP模型的精度（0.93）大大提高（0.84）。此外，我们表明深度学习NLP可以成功识别没有痴呆相关的ICD代码或药物的痴呆症患者。