超级解决全球气候模拟的粗略产出，称为缩减，对于需要长期气候变化预测的系统做出政治和社会决策至关重要。但是，现有的快速超分辨率技术尚未保留气候数据的空间相关性，这在我们以空间扩展（例如运输基础设施的开发）处理系统时尤其重要。本文中，我们展示了基于对抗性的网络的机器学习，使我们能够在降尺度中正确重建区域间空间相关性，并高达五十，同时保持像素统计的一致性。与测量的温度和降水分布的气象数据的直接比较表明，整合气候上重要的物理信息对于准确的缩减至关重要，这促使我们称我们的方法称为$ \ pi $ srgan（物理学知情的超级分辨率生成生成的对手网络）。本方法对气候变化影响的区域间一致评估具有潜在的应用。

在一系列软物质系统中广泛观察到玻璃过渡。但是，尽管有多年的研究，这些转变的物理机制仍然未知。特别是，一个重要的未解决的问题是玻璃转变是否伴随着特征静态结构的相关长度的分歧。最近，提出了一种可以从纯精度的纯静态信息中预测长期动态的方法。但是，即使是这种方法也不通用，并且对于KOB（Andersen系统）而言，这是典型的玻璃形成液体模型。在这项研究中，我们开发了一种使用机器学习或尤其是卷积神经网络提取眼镜的特征结构的方法。特别是，我们通过量化网络做出的决策的理由来提取特征结构。我们考虑了两个质量不同的玻璃形成二进制系统，并通过与几个既定结构指标进行比较，我们证明我们的系统可以识别依赖于系统细节的特征结构。令人惊讶的是，提取的结构与热波动中的非平衡衰老动力学密切相关。

Many e-commerce marketplaces offer their users fast delivery options for free to meet the increasing needs of users, imposing an excessive burden on city logistics. Therefore, understanding e-commerce users' preference for delivery options is a key to designing logistics policies. To this end, this study designs a stated choice survey in which respondents are faced with choice tasks among different delivery options and time slots, which was completed by 4,062 users from the three major metropolitan areas in Japan. To analyze the data, mixed logit models capturing taste heterogeneity as well as flexible substitution patterns have been estimated. The model estimation results indicate that delivery attributes including fee, time, and time slot size are significant determinants of the delivery option choices. Associations between users' preferences and socio-demographic characteristics, such as age, gender, teleworking frequency and the presence of a delivery box, were also suggested. Moreover, we analyzed two willingness-to-pay measures for delivery, namely, the value of delivery time savings (VODT) and the value of time slot shortening (VOTS), and applied a non-semiparametric approach to estimate their distributions in a data-oriented manner. Although VODT has a large heterogeneity among respondents, the estimated median VODT is 25.6 JPY/day, implying that more than half of the respondents would wait an additional day if the delivery fee were increased by only 26 JPY, that is, they do not necessarily need a fast delivery option but often request it when cheap or almost free. Moreover, VOTS was found to be low, distributed with the median of 5.0 JPY/hour; that is, users do not highly value the reduction in time slot size in monetary terms. These findings on e-commerce users' preferences can help in designing levels of service for last-mile delivery to significantly improve its efficiency.

Distributed representations of words encode lexical semantic information, but how is that information encoded in word embeddings? Focusing on the skip-gram with negative-sampling method, we show theoretically and experimentally that the squared norm of word embedding encodes the information gain defined by the Kullback-Leibler divergence of the co-occurrence distribution of a word to the unigram distribution of the corpus. Furthermore, through experiments on tasks of keyword extraction, hypernym prediction, and part-of-speech discrimination, we confirmed that the KL divergence and the squared norm of embedding work as a measure of the informativeness of a word provided that the bias caused by word frequency is adequately corrected.

In this paper, we propose a novel technique to accelerate Ising machines hyperparameter tuning. Firstly, we define Ising machine performance and explain the goal of hyperparameter tuning in regard to this performance definition. Secondly, we compare well-known hyperparameter tuning techniques, namely random sampling and Tree-structured Parzen Estimator (TPE) on different combinatorial optimization problems. Thirdly, we propose a new convergence acceleration method for TPE which we call "FastConvergence".It aims at limiting the number of required TPE trials to reach best performing hyperparameter values combination. We compare FastConvergence to previously mentioned well-known hyperparameter tuning techniques to show its effectiveness. For experiments, well-known Travel Salesman Problem (TSP) and Quadratic Assignment Problem (QAP) instances are used as input. The Ising machine used is Fujitsu's third generation Digital Annealer (DA). Results show, in most cases, FastConvergence can reach similar results to TPE alone within less than half the number of trials.

Correctly recognizing the behaviors of children with Autism Spectrum Disorder (ASD) is of vital importance for the diagnosis of Autism and timely early intervention. However, the observation and recording during the treatment from the parents of autistic children may not be accurate and objective. In such cases, automatic recognition systems based on computer vision and machine learning (in particular deep learning) technology can alleviate this issue to a large extent. Existing human action recognition models can now achieve persuasive performance on challenging activity datasets, e.g. daily activity, and sports activity. However, problem behaviors in children with ASD are very different from these general activities, and recognizing these problem behaviors via computer vision is less studied. In this paper, we first evaluate a strong baseline for action recognition, i.e. Video Swin Transformer, on two autism behaviors datasets (SSBD and ESBD) and show that it can achieve high accuracy and outperform the previous methods by a large margin, demonstrating the feasibility of vision-based problem behaviors recognition. Moreover, we propose language-assisted training to further enhance the action recognition performance. Specifically, we develop a two-branch multimodal deep learning framework by incorporating the "freely available" language description for each type of problem behavior. Experimental results demonstrate that incorporating additional language supervision can bring an obvious performance boost for the autism problem behaviors recognition task as compared to using the video information only (i.e. 3.49% improvement on ESBD and 1.46% on SSBD).

在肉牛的库存中，基于计算机视觉的方法已被广泛用于监测牛状况（例如，物理，生理学和健康）。为此，准确有效的牛行动是一种先决条件。通常，大多数现有模型仅限于个人行为，这些行为使用基于视频的方法提取时空特征来识别每只牛的个体作用。但是，牛之间存在社会性，它们的相互作用通常反映了重要条件，例如Estrus以及基于视频的方法忽略了模型的实时功能。基于这一点，我们解决了本文中单个框架中牛之间的实时识别的具有挑战性的任务。我们方法的管道包括两个主要模块：牛本地化网络和交互识别网络。在每时每刻，牛本地化网络都会从每个检测到的牛输出高质量的互动建议，并将其输入具有三流体系结构的交互识别网络。这样的三流网络使我们能够融合与识别交互有关的不同功能。具体而言，这三种功能是一个视觉特征，它提取了互动建议的外观表示，这是反映牛之间空间关系的几何特征，以及一种语义特征，它捕获了我们对个人动作和相互作用之间关系的先验知识牛。此外，为了解决数量不足的标记数据问题，我们基于自我监督学习的模型预先培训。定性和定量评估证明了我们框架作为实时识别牛相互作用的有效方法的性能。

在人工智能和音乐领域中，从歌词中产生旋律是一项有趣而又具有挑战性的任务。但是，保持输入歌词和生成旋律之间的一致性的困难限制了以前作品的发电质量。在我们的建议中，我们演示了我们提出的可解释的歌词到循环的生成系统，该系统可以与用户互动以了解生成过程并重新创建所需的歌曲。为了提高与歌词匹配的旋律生成的可靠性，相互利用以增强歌词和生成的旋律之间的一致性。利用Gumbel-Softmax来解决通过生成对抗网络（GAN）生成离散音乐属性的非差异性问题。此外，发电机的预测概率输出用于推荐音乐属性。与我们的歌词到旋律生成系统互动，用户可以收听生成的AI歌曲，并通过从推荐的音乐属性中选择来重新创建新歌。

尽管递归logit（RL）模型最近很受欢迎，并且导致了许多应用和扩展，但关于价值函数计算的重要数值问题仍未解决。对于模型估计，此问题尤其重要，在此期间，参数会更新每个迭代，并可能违反模型可行条件。为了解决模型估计中值函数的数值问题，本研究对Oyama和Hato（2019）提出的Prism受限的RL（Prism-RL）模型进行了广泛的分析，该模型的路径集受Prism的约束。根据状态扩展的网络表示定义。数值实验已显示出参数估计的Prism-RL模型的两个重要属性。首先，即使在无法估算原始RL模型的情况下，基于PRISM的方法都可以进行稳定的估计。我们还成功地捕获了街道绿色对行人路线选择的积极影响。其次，通过隐式限制大型绕道或许多循环的路径，PRISM-RL模型比RL模型获得了更高的拟合和预测性能优点。定义基于棱镜的路径以数据为导向的方式，我们证明了描述更现实的路线选择行为的Prism-RL模型的可能性。稳定地捕获正网络属性的同时保留路径替代方案的多样性可显着扩展RL模型的实际适用性。

已经对光子加速器进行了深入的研究，以提供增强的信息处理能力，从而受益于物理过程的独特属性。最近，据报道，从激光器（Laser Chaos）的混沌振荡超快时间序列提供了解决多臂匪徒（MAB）问题或决策问题的能力。此外，已经证实，激光混乱的负相关时间域结构有助于加速决策。但是，为什么相关时间序列加速决策的基本机制尚不清楚。在这项研究中，我们展示了一个理论模型，以说明相关时间序列加速决策的理论模型。我们首先证实了使用傅立叶变换替代方法来解决两臂匪徒问题的固有时间序列的负自相关的有效性。我们提出了一个理论模型，该模型涉及遵守决策系统和系统内部状态的相关时间序列，并受到相关的随机步行的启发。我们证明，该理论分析得出的性能与数值模拟非常吻合，该模拟证实了所提出的模型的有效性并导致最佳系统设计。本研究为提高相关时间序列的有效性铺平了道路，从而影响人工智能和其他应用。