优化昂贵以评估黑盒功能在包含D对象的所有排列中的输入空间是许多真实应用的重要问题。例如，在硬件设计中放置功能块以通过仿真优化性能。总体目标是最小化函数评估的数量，以找到高性能的排列。使用贝叶斯优化（BO）框架解决这个问题的关键挑战是折衷统计模型的复杂性和采集功能优化的途径。在本文中，我们提出并评估了博的两个算法（BOPS）。首先，BOPS-T采用高斯工艺（GP）代理模型与KENDALL内核和基于Thompson采样的Trocable采集功能优化方法，以选择评估的排列顺序。其次，BOPS-H采用GP代理模型与锦葵内核和启发式搜索方法，以优化预期的改进采集功能。理论上，从理论上分析BOPS-T的性能，以表明他们的遗憾增加了亚线性。我们对多种综合和现实世界基准测试的实验表明，BOPS-T和BOPS-H均优于组合空间的最先进的BO算法。为了推动未来的对这个重要问题的研究，我们为社区提供了新的资源和现实世界基准。

我们考虑使用昂贵的黑盒功能评估优化组合空间（例如，序列，树木和图形）的问题。例如，使用物理实验室实验优化用于药物设计的分子。贝叶斯优化（BO）是一种有效的框架，可以通过智能地选择由学习的代理模型引导的高实用程序的输入来解决这些问题。最近用于组合空间的BO方法是通过使用深生成模型（DGMS）学习结构的潜在表示来减少到连续空间。从连续空间的所选输入被解码为用于执行功能评估的离散结构。然而，潜在空间上的代理模型仅使用DGM学习的信息，这可能不具有所需的感应偏压来近似于目标黑盒功能。为了克服这篇缺点，本文提出了一种原则方法，称为梯子。关键的想法是定义一种新颖的结构耦合内核，该内核明确地将结构信息与解码结构与学习的潜空间表示进行了解，以获得更好的代理建模。我们对现实世界基准测试的实验表明，梯子显着改善了纬度的潜伏空间方法，并表现出更好或更好地与最先进的方法。

我们考虑使用昂贵的功能评估（也称为实验）的黑匣子多目标优化（MOO）的问题，其中目标是通过最小化实验的总资源成本来近似真正的帕累托解决方案。例如，在硬件设计优化中，我们需要使用昂贵的计算模拟找到权衡性能，能量和面积开销的设计。关键挑战是选择使用最小资源揭示高质量解决方案的实验顺序。在本文中，我们提出了一种基于输出空间熵（OSE）搜索原理来解决MOO问题的一般框架：选择最大化每单位资源成本的信息的实验，这是真正的帕累托前线所获得的信息。我们适当地实例化了OSE搜索的原理，以导出以下四个Moo问题设置的高效算法：1）最基本的EM单一保真设置，实验昂贵且准确; 2）处理EM黑匣子约束}在不执行实验的情况下无法进行评估; 3）离散的多保真设置，实验可以在消耗的资源量和评估准确度时变化; 4）EM连续保真设置，其中连续函数近似导致巨大的实验空间。不同综合和现实世界基准测试的实验表明，基于OSE搜索的算法在既有计算效率和MOO解决方案的准确性方面改进了最先进的方法。

Persuasion modeling is a key building block for conversational agents. Existing works in this direction are limited to analyzing textual dialogue corpus. We argue that visual signals also play an important role in understanding human persuasive behaviors. In this paper, we introduce the first multimodal dataset for modeling persuasion behaviors. Our dataset includes 199 dialogue transcriptions and videos captured in a multi-player social deduction game setting, 26,647 utterance level annotations of persuasion strategy, and game level annotations of deduction game outcomes. We provide extensive experiments to show how dialogue context and visual signals benefit persuasion strategy prediction. We also explore the generalization ability of language models for persuasion modeling and the role of persuasion strategies in predicting social deduction game outcomes. Our dataset, code, and models can be found at https://persuasion-deductiongame.socialai-data.org.

The exercise of detecting similar bug reports in bug tracking systems is known as duplicate bug report detection. Having prior knowledge of a bug report's existence reduces efforts put into debugging problems and identifying the root cause. Rule and Query-based solutions recommend a long list of potential similar bug reports with no clear ranking. In addition, triage engineers are less motivated to spend time going through an extensive list. Consequently, this deters the use of duplicate bug report retrieval solutions. In this paper, we have proposed a solution using a combination of NLP techniques. Our approach considers unstructured and structured attributes of a bug report like summary, description and severity, impacted products, platforms, categories, etc. It uses a custom data transformer, a deep neural network, and a non-generalizing machine learning method to retrieve existing identical bug reports. We have performed numerous experiments with significant data sources containing thousands of bug reports and showcased that the proposed solution achieves a high retrieval accuracy of 70% for recall@5.

Low-field (LF) MRI scanners have the power to revolutionize medical imaging by providing a portable and cheaper alternative to high-field MRI scanners. However, such scanners are usually significantly noisier and lower quality than their high-field counterparts. The aim of this paper is to improve the SNR and overall image quality of low-field MRI scans to improve diagnostic capability. To address this issue, we propose a Nested U-Net neural network architecture super-resolution algorithm that outperforms previously suggested deep learning methods with an average PSNR of 78.83 and SSIM of 0.9551. We tested our network on artificial noisy downsampled synthetic data from a major T1 weighted MRI image dataset called the T1-mix dataset. One board-certified radiologist scored 25 images on the Likert scale (1-5) assessing overall image quality, anatomical structure, and diagnostic confidence across our architecture and other published works (SR DenseNet, Generator Block, SRCNN, etc.). We also introduce a new type of loss function called natural log mean squared error (NLMSE). In conclusion, we present a more accurate deep learning method for single image super-resolution applied to synthetic low-field MRI via a Nested U-Net architecture.

Experiments using large numbers of miniature swarm robots are desirable to teach, study, and test multi-robot and swarm intelligence algorithms and their applications. To realize the full potential of a swarm robot, it should be capable of not only motion but also sensing, computing, communication, and power management modules with multiple options. Current swarm robot platforms developed for commercial and academic research purposes lack several of these critical attributes by focusing only on a few of these aspects. Therefore, in this paper, we propose the HeRoSwarm, a fully-capable swarm robot platform with open-source hardware and software support. The proposed robot hardware is a low-cost design with commercial off-the-shelf components that uniquely integrates multiple sensing, communication, and computing modalities with various power management capabilities into a tiny footprint. Moreover, our swarm robot with odometry capability with Robot Operating Systems (ROS) support is unique in its kind. This simple yet powerful swarm robot design has been extensively verified with different prototyping variants and multi-robot experimental demonstrations.

Time Series Forecasting has been an active area of research due to its many applications ranging from network usage prediction, resource allocation, anomaly detection, and predictive maintenance. Numerous publications published in the last five years have proposed diverse sets of objective loss functions to address cases such as biased data, long-term forecasting, multicollinear features, etc. In this paper, we have summarized 14 well-known regression loss functions commonly used for time series forecasting and listed out the circumstances where their application can aid in faster and better model convergence. We have also demonstrated how certain categories of loss functions perform well across all data sets and can be considered as a baseline objective function in circumstances where the distribution of the data is unknown. Our code is available at GitHub: https://github.com/aryan-jadon/Regression-Loss-Functions-in-Time-Series-Forecasting-Tensorflow.

学习在线推荐模型的关键挑战之一是时间域移动，这会导致培训与测试数据分布之间的不匹配以及域的概括错误。为了克服，我们建议学习一个未来的梯度生成器，该生成器可以预测培训未来数据分配的梯度信息，以便可以对建议模型进行培训，就像我们能够展望其部署的未来一样。与批处理更新相比，我们的理论表明，所提出的算法达到了较小的时间域概括误差，该误差通过梯度变异项在局部遗憾中衡量。我们通过与各种代表性基线进行比较来证明经验优势。

仇恨言论以贬义的评论以多种形式针对社区，并使人类退后一步。 Hatexplain是最近出版的第一个数据集，用于以理由的形式使用带注释的跨度，以及语音分类类别和有针对性的社区，以使分类更具人性化，可解释，准确和偏见。我们调整BERT以理由和阶级预测的形式执行此任务，并比较我们对跨精度，解释性和偏见的不同指标的性能。我们的新颖性是三倍。首先，我们尝试具有不同重要性值的合并理由类损失。其次，我们对理由的地面真相注意值进行了广泛的实验。随着保守和宽大的关注，我们比较了hatexplain模型的性能并检验我们的假设。第三，为了改善模型中的意外偏见，我们使用目标社区单词的掩盖，并注意偏见和解释性指标的改善。总体而言，我们成功地实现了模型的解释性，偏差删除和对原始BERT实施的几个增量改进。