人工智能（AI）球员已经获得了像Go，国际象棋和奥赛罗（Reversi）这样的游戏的超人技能。换句话说，AI球员作为人类球员的对手变得太强。然后，我们不会与AI播放器一起玩棋盘游戏。为了娱乐人类球员，AI球员必须自动平衡其人类球员的技能。为了解决这个问题，我提出了一个具有动态难度调整的AI播放器的Alphadda，基于Alphazero。 alphadda包括一个深神经网络（DNN）和蒙特卡罗树搜索，如alphazero。 alphadda估计游戏状态的值仅使用DNN的板状态，并根据值改变其技能。 Alphadda可以仅使用游戏的状态调整Alphadda技能，而无需先验对对手的知识。在本研究中，Alphadda播放Connect4,6x6 othello，使用6x6尺寸板，与其他AI代理商使用6x6尺寸板，othello。其他AI代理商是alphazero，蒙特卡罗树搜索，minimax算法和随机播放器。本研究表明，除随机玩家外，alphadda实现了与其他AI代理的技能。 alphadda的DDA能力来自于从游戏状态的值的准确估计。我们将能够为任何游戏使用Alphadda的方法，因为DNN可以估计来自状态的值。

Classification bandits are multi-armed bandit problems whose task is to classify a given set of arms into either positive or negative class depending on whether the rate of the arms with the expected reward of at least h is not less than w for given thresholds h and w. We study a special classification bandit problem in which arms correspond to points x in d-dimensional real space with expected rewards f(x) which are generated according to a Gaussian process prior. We develop a framework algorithm for the problem using various arm selection policies and propose policies called FCB and FTSV. We show a smaller sample complexity upper bound for FCB than that for the existing algorithm of the level set estimation, in which whether f(x) is at least h or not must be decided for every arm's x. Arm selection policies depending on an estimated rate of arms with rewards of at least h are also proposed and shown to improve empirical sample complexity. According to our experimental results, the rate-estimation versions of FCB and FTSV, together with that of the popular active learning policy that selects the point with the maximum variance, outperform other policies for synthetic functions, and the version of FTSV is also the best performer for our real-world dataset.

Drug-Drug Interactions (DDIs) prediction is an essential issue in the molecular field. Traditional methods of observing DDIs in medical experiments require plenty of resources and labor. In this paper, we present a computational model dubbed MedKGQA based on Graph Neural Networks to automatically predict the DDIs after reading multiple medical documents in the form of multi-hop machine reading comprehension. We introduced a knowledge fusion system to obtain the complete nature of drugs and proteins and exploited a graph reasoning system to infer the drugs and proteins contained in the documents. Our model significantly improves the performance compared to previous state-of-the-art models on the QANGAROO MedHop dataset, which obtained a 4.5% improvement in terms of DDIs prediction accuracy.

The black-box nature of end-to-end speech translation (E2E ST) systems makes it difficult to understand how source language inputs are being mapped to the target language. To solve this problem, we would like to simultaneously generate automatic speech recognition (ASR) and ST predictions such that each source language word is explicitly mapped to a target language word. A major challenge arises from the fact that translation is a non-monotonic sequence transduction task due to word ordering differences between languages -- this clashes with the monotonic nature of ASR. Therefore, we propose to generate ST tokens out-of-order while remembering how to re-order them later. We achieve this by predicting a sequence of tuples consisting of a source word, the corresponding target words, and post-editing operations dictating the correct insertion points for the target word. We examine two variants of such operation sequences which enable generation of monotonic transcriptions and non-monotonic translations from the same speech input simultaneously. We apply our approach to offline and real-time streaming models, demonstrating that we can provide explainable translations without sacrificing quality or latency. In fact, the delayed re-ordering ability of our approach improves performance during streaming. As an added benefit, our method performs ASR and ST simultaneously, making it faster than using two separate systems to perform these tasks.

众所周知，大数据挖掘是数据科学的重要任务，因为它可以提供有用的观察结果和隐藏在给定的大数据集中的新知识。基于接近性的数据分析尤其在许多现实生活中使用。在这样的分析中，通常采用了与K最近的邻居的距离，因此其主瓶颈来自数据检索。为提高这些分析的效率做出了许多努力。但是，他们仍然会产生巨大的成本，因为它们基本上需要许多数据访问。为了避免此问题，我们提出了一种机器学习技术，该技术可以快速准确地估算给定查询的K-NN距离（即与K最近的邻居的距离）。我们训练完全连接的神经网络模型，并利用枢轴来实现准确的估计。我们的模型旨在具有有用的优势：它一次不距离K-NN，其推理时间为O（1）（未产生数据访问），但保持高精度。我们对实际数据集的实验结果和案例研究证明了解决方案的效率和有效性。

我们通过单数值分解（SVD）近似游戏TIC-TAC-TAC的评估函数，并研究了近似准确性对获胜率的影响。我们首先准备了TIC-TAC-TOE的完美评估函数，并通过将评估函数视为第九阶张量来进行低级近似。我们发现，我们可以将评估功能的信息量减少70％，而不会显着降低性能。近似准确性和获胜率密切相关，但不完全成比例。我们还研究了评估函数的分解方法如何影响性能。我们考虑了两种分解方法：关于评估函数的简单SVD作为矩阵和高阶SVD（HOSVD）的Tucker分解。在相同的压缩比下，通过HOSVD获得的近似评估函数的策略表现出明显高于SVD获得的策略。这些结果表明，SVD可以有效地压缩棋盘游戏策略，并有一种取决于游戏的最佳压缩方法。

本文介绍了一种系统集成方法，用于一种6-DOF（自由度）协作机器人，以操作移液液的移液液。它的技术发展是三倍。首先，我们设计了用于握住和触发手动移液器的最终效果。其次，我们利用协作机器人的优势来识别基于公认姿势的实验室姿势和计划的机器人运动。第三，我们开发了基于视觉的分类器来预测和纠正定位误差，从而精确地附着在一次性技巧上。通过实验和分析，我们确认开发的系统，尤其是计划和视觉识别方法，可以帮助确保高精度和柔性液体分配。开发的系统适用于低频，高更改的生化液体分配任务。我们预计它将促进协作机器人的部署进行实验室自动化，从而提高实验效率，而不会显着自定义实验室环境。

我们提出了一种从稀疏多视图RGB视频重建可控隐式3D人类模型的新方法。我们的方法在网格表面点上定义神经场景表示，并从人体网格的表面签名距离。我们识别出一种无法区分的问题，当3D空间中的点映射到其最近的网格上的最近的表面点时出现的问题，用于学习表面对齐的神经场景表示。要解决此问题，我们将使用与修改的顶点正常的重心插值提出将点投影到网状表面上。与Zju-Mocap和Human3.6m数据集的实验表明，我们的方法在比现有方法的新颖性和新型姿态合成中实现了更高的质量。我们还表明，我们的方法很容易支持身体形状和衣服的控制。

提出了一种用于建模粒子促进剂中的梁壁相互作用的无网线方法。我们的方法的关键思想是使用深神经网络作为替代涉及粒子束的一组部分微分方程的替代品，以及表面阻抗概念。所提出的方法应用于具有薄导电涂层的加速器真空室的耦合阻抗，并与现有的分析配方相比验证。

Multi-hop machine reading comprehension is a challenging task in natural language processing, which requires more reasoning ability across multiple documents. Spectral models based on graph convolutional networks grant inferring abilities and lead to competitive results. However, part of them still faces the challenge of analyzing the reasoning in a human-understandable way. Inspired by the concept of the Grandmother Cells in cognitive neuroscience, a spatial graph attention framework named ClueReader was proposed in this paper, imitating the procedure. This model is designed to assemble the semantic features in multi-level representations and automatically concentrate or alleviate information for reasoning via the attention mechanism. The name ClueReader is a metaphor for the pattern of the model: regard the subjects of queries as the start points of clues, take the reasoning entities as bridge points, consider the latent candidate entities as the grandmother cells, and the clues end up in candidate entities. The proposed model allows us to visualize the reasoning graph, then analyze the importance of edges connecting two entities and the selectivity in the mention and candidate nodes, which can be easier to be comprehended empirically. The official evaluations in the open-domain multi-hop reading dataset WikiHop and the Drug-drug Interactions dataset MedHop prove the validity of our approach and show the probability of the application of the model in the molecular biology domain.