语言模型既展示了定量的改进，又展示了新的定性功能，随着规模的增加。尽管它们具有潜在的变革性影响，但这些新能力的特征却很差。为了为未来的研究提供信息，为破坏性的新模型能力做准备，并改善社会有害的效果，至关重要的是，我们必须了解目前和近乎未来的能力和语言模型的局限性。为了应对这一挑战，我们介绍了超越模仿游戏基准（Big Bench）。 Big Bench目前由204个任务组成，由132家机构的442位作者贡献。任务主题是多样的，从语言学，儿童发展，数学，常识性推理，生物学，物理学，社会偏见，软件开发等等。 Big-Bench专注于被认为超出当前语言模型的功能的任务。我们评估了OpenAI的GPT型号，Google内部密集变压器体系结构和大型基础上的开关稀疏变压器的行为，跨越了数百万到数十亿个参数。此外，一个人类专家评估者团队执行了所有任务，以提供强大的基准。研究结果包括：模型性能和校准都随规模改善，但绝对的术语（以及与评估者的性能相比）；在模型类中的性能非常相似，尽管带有稀疏性。逐渐和预测的任务通常涉及大量知识或记忆成分，而在临界规模上表现出“突破性”行为的任务通常涉及多个步骤或组成部分或脆性指标；社交偏见通常会随着含糊不清的环境而随着规模而增加，但这可以通过提示来改善。

深度图用于从3D渲染到2D图像效应（例如散景）的广泛应用。但是，单个图像深度估计（侧）模型预测的人通常无法捕获对象中的孤立孔和/或具有不准确的边界区域。同时，使用商业自动掩蔽工具或现成的分割和垫子的方法，甚至是通过手动编辑，使用商业自动掩盖工具或现成的方法更容易获得。因此，在本文中，我们提出了一个新的掩盖引导深度细化的问题，该问题利用通用掩模来完善侧面模型的深度预测。我们的框架执行了分层的细化和介入/架设，将深度图分解为两个由掩码和倒置面罩表示的单独的层。由于具有深度和掩码注释的数据集很少，因此我们提出了一种使用任意掩码和RGB-D数据集的自我监督学习方案。我们从经验上表明，我们的方法对不同类型的掩模和初始深度预测具有鲁棒性，可以准确地完善内部和外掩模边界区域的深度值。我们通过消融研究进一步分析了我们的模型，并证明了实际应用的结果。可以在https://sooyekim.github.io/maskdepth/上找到更多信息。

前列腺癌是美国男人的第二致致命癌症。虽然磁共振成像（MRI）越来越多地用于引导前列腺癌诊断的靶向活组织检查，但其效用仍然受到限制，因为假阳性和假否定的高率以及较低的读者协议。机器学习方法在前列腺MRI上检测和定位癌症可以帮助标准化放射科学诠释。然而，现有的机器学习方法不仅在模型架构中不等，而且还可以在用于模型培训的地面真理标签策略中。在这项研究中，我们比较不同的标记策略，即病理证实放射科标签，整个安装组织病理学图像上的病理学家标签，以及病变水平和像素级数字病理学家标签（先前验证了组织病理学图像上的深层学习算法以预测像素 - 整个安装组织病理学图像上的Gleason模式）。我们分析这些标签对训练有素的机器学习模型的性能的影响。我们的实验表明，用它们培训的（1）放射科标签和模型可能会错过癌症，或低估癌症程度，（2）与他们培训的数字病理学家标签和模型与病理学家标签有高度的一致性，而（3）用数字病理学家培训的模型标签在两种不同疾病分布的两种不同群组中达到最佳性能，而不管使用的模型建筑如何。数字病理学家标签可以减少与人类注释相关的挑战，包括劳动力，时间，和读者间变异性，并且可以通过使可靠的机器学习模型进行培训来检测和定位前列腺癌，帮助弥合前列腺放射学和病理学之间的差距在MRI。

临床问题应答（QA）旨在根据临床文本自动回答医疗专业人员的问题。研究表明，在一个语料库上培训的神经QA模型可能对来自不同研究所或不同患者组的新临床文本概括，其中大规模的QA对不容易获得模型再培训。为了解决这一挑战，我们提出了一个简单但有效的框架CliniQG4QA，它利用问题生成（QG）在新的临床环境中综合QA对，并在不需要手动注释的情况下提升QA模型。为了生成对训练QA模型至关重要的不同类型的问题，我们进一步引入了基于SEQ2SEQ的问题短语预测（QPP）模块，可以与大多数现有的QG模型一起使用以使生成多样化。我们的综合实验结果表明，我们的框架产生的QA​​语料库可以改善新上下文的QA模型（在完全匹配方面最高8％的绝对增益），QPP模块在实现增益方面发挥着至关重要的作用。

New architecture GPUs like A100 are now equipped with multi-instance GPU (MIG) technology, which allows the GPU to be partitioned into multiple small, isolated instances. This technology provides more flexibility for users to support both deep learning training and inference workloads, but efficiently utilizing it can still be challenging. The vision of this paper is to provide a more comprehensive and practical benchmark study for MIG in order to eliminate the need for tedious manual benchmarking and tuning efforts. To achieve this vision, the paper presents MIGPerf, an open-source tool that streamlines the benchmark study for MIG. Using MIGPerf, the authors conduct a series of experiments, including deep learning training and inference characterization on MIG, GPU sharing characterization, and framework compatibility with MIG. The results of these experiments provide new insights and guidance for users to effectively employ MIG, and lay the foundation for further research on the orchestration of hybrid training and inference workloads on MIGs. The code and results are released on https://github.com/MLSysOps/MIGProfiler. This work is still in progress and more results will be published soon.

Tobacco origin identification is significantly important in tobacco industry. Modeling analysis for sensor data with near infrared spectroscopy has become a popular method for rapid detection of internal features. However, for sensor data analysis using traditional artificial neural network or deep network models, the training process is extremely time-consuming. In this paper, a novel broad learning system with Takagi-Sugeno (TS) fuzzy subsystem is proposed for rapid identification of tobacco origin. Incremental learning is employed in the proposed method, which obtains the weight matrix of the network after a very small amount of computation, resulting in much shorter training time for the model, with only about 3 seconds for the extra step training. The experimental results show that the TS fuzzy subsystem can extract features from the near infrared data and effectively improve the recognition performance. The proposed method can achieve the highest prediction accuracy (95.59 %) in comparison to the traditional classification algorithms, artificial neural network, and deep convolutional neural network, and has a great advantage in the training time with only about 128 seconds.

Accurate modeling of ship performance is crucial for the shipping industry to optimize fuel consumption and subsequently reduce emissions. However, predicting the speed-power relation in real-world conditions remains a challenge. In this study, we used in-service monitoring data from multiple vessels with different hull shapes to compare the accuracy of data-driven machine learning (ML) algorithms to traditional methods for assessing ship performance. Our analysis consists of two main parts: (1) a comparison of sea trial curves with calm-water curves fitted on operational data, and (2) a benchmark of multiple added wave resistance theories with an ML-based approach. Our results showed that a simple neural network outperformed established semi-empirical formulas following first principles. The neural network only required operational data as input, while the traditional methods required extensive ship particulars that are often unavailable. These findings suggest that data-driven algorithms may be more effective for predicting ship performance in practical applications.

As a common appearance defect of concrete bridges, cracks are important indices for bridge structure health assessment. Although there has been much research on crack identification, research on the evolution mechanism of bridge cracks is still far from practical applications. In this paper, the state-of-the-art research on intelligent theories and methodologies for intelligent feature extraction, data fusion and crack detection based on data-driven approaches is comprehensively reviewed. The research is discussed from three aspects: the feature extraction level of the multimodal parameters of bridge cracks, the description level and the diagnosis level of the bridge crack damage states. We focus on previous research concerning the quantitative characterization problems of multimodal parameters of bridge cracks and their implementation in crack identification, while highlighting some of their major drawbacks. In addition, the current challenges and potential future research directions are discussed.

Two approaches to AI, neural networks and symbolic systems, have been proven very successful for an array of AI problems. However, neither has been able to achieve the general reasoning ability required for human-like intelligence. It has been argued that this is due to inherent weaknesses in each approach. Luckily, these weaknesses appear to be complementary, with symbolic systems being adept at the kinds of things neural networks have trouble with and vice-versa. The field of neural-symbolic AI attempts to exploit this asymmetry by combining neural networks and symbolic AI into integrated systems. Often this has been done by encoding symbolic knowledge into neural networks. Unfortunately, although many different methods for this have been proposed, there is no common definition of an encoding to compare them. We seek to rectify this problem by introducing a semantic framework for neural-symbolic AI, which is then shown to be general enough to account for a large family of neural-symbolic systems. We provide a number of examples and proofs of the application of the framework to the neural encoding of various forms of knowledge representation and neural network. These, at first sight disparate approaches, are all shown to fall within the framework's formal definition of what we call semantic encoding for neural-symbolic AI.

Diffusion models have shown a great ability at bridging the performance gap between predictive and generative approaches for speech enhancement. We have shown that they may even outperform their predictive counterparts for non-additive corruption types or when they are evaluated on mismatched conditions. However, diffusion models suffer from a high computational burden, mainly as they require to run a neural network for each reverse diffusion step, whereas predictive approaches only require one pass. As diffusion models are generative approaches they may also produce vocalizing and breathing artifacts in adverse conditions. In comparison, in such difficult scenarios, predictive models typically do not produce such artifacts but tend to distort the target speech instead, thereby degrading the speech quality. In this work, we present a stochastic regeneration approach where an estimate given by a predictive model is provided as a guide for further diffusion. We show that the proposed approach uses the predictive model to remove the vocalizing and breathing artifacts while producing very high quality samples thanks to the diffusion model, even in adverse conditions. We further show that this approach enables to use lighter sampling schemes with fewer diffusion steps without sacrificing quality, thus lifting the computational burden by an order of magnitude. Source code and audio examples are available online (https://uhh.de/inf-sp-storm).