Topological data analysis (TDA) is a branch of computational mathematics, bridging algebraic topology and data science, that provides compact, noise-robust representations of complex structures. Deep neural networks (DNNs) learn millions of parameters associated with a series of transformations defined by the model architecture, resulting in high-dimensional, difficult-to-interpret internal representations of input data. As DNNs become more ubiquitous across multiple sectors of our society, there is increasing recognition that mathematical methods are needed to aid analysts, researchers, and practitioners in understanding and interpreting how these models' internal representations relate to the final classification. In this paper, we apply cutting edge techniques from TDA with the goal of gaining insight into the interpretability of convolutional neural networks used for image classification. We use two common TDA approaches to explore several methods for modeling hidden-layer activations as high-dimensional point clouds, and provide experimental evidence that these point clouds capture valuable structural information about the model's process. First, we demonstrate that a distance metric based on persistent homology can be used to quantify meaningful differences between layers, and we discuss these distances in the broader context of existing representational similarity metrics for neural network interpretability. Second, we show that a mapper graph can provide semantic insight into how these models organize hierarchical class knowledge at each layer. These observations demonstrate that TDA is a useful tool to help deep learning practitioners unlock the hidden structures of their models.

We present MegaBlocks, a system for efficient Mixture-of-Experts (MoE) training on GPUs. Our system is motivated by the limitations of current frameworks, which restrict the dynamic routing in MoE layers to satisfy the constraints of existing software and hardware. These formulations force a tradeoff between model quality and hardware efficiency, as users must choose between dropping tokens from the computation or wasting computation and memory on padding. To address these limitations, we reformulate MoE computation in terms of block-sparse operations and develop new block-sparse GPU kernels that efficiently handle the dynamism present in MoEs. Our approach never drops tokens and maps efficiently to modern hardware, enabling end-to-end training speedups of up to 40% over MoEs trained with the state-of-the-art Tutel library and 2.4x over DNNs trained with the highly-optimized Megatron-LM framework.

自上而下的方法主导了3D人类姿势和形状估计的领域，因为它们与人类的检测脱钩，并使研究人员能够专注于核心问题。但是，裁剪是他们的第一步，从一开始就丢弃了位置信息，这使自己无法准确预测原始摄像机坐标系中的全局旋转。为了解决此问题，我们建议将完整框架（悬崖）的位置信息携带到此任务中。具体而言，我们通过将裁剪图像功能与其边界盒信息连接在一起来养活更多的整体功能来悬崖。我们通过更广泛的全帧视图来计算2D再投影损失，进行了类似于图像中投射的人的投影过程。克里夫（Cliff）通过全球态度感知信息进行了喂养和监督，直接预测全球旋转以及更准确的明确姿势。此外，我们提出了一个基于Cliff的伪基真实注释，该注释为野外2D数据集提供了高质量的3D注释，并为基于回归的方法提供了至关重要的全面监督。对流行基准测试的广泛实验表明，悬崖的表现要超过先前的艺术，并在Agora排行榜上获得了第一名（SMPL-Algorithms曲目）。代码和数据可在https://github.com/huawei-noah/noah-research/tree/master/cliff中获得。

免疫反应是一个动态过程，通过该过程，身体决定抗原是自我还是非自然。这种动态过程的状态由构成该决策过程的炎症和监管参与者的相对平衡和种群定义。免疫疗法的目的，例如因此，类风湿关节炎（RA）是为了使免疫状态偏向于监管参与者，从而在反应中关闭自身免疫性途径。尽管有几种已知的免疫疗法方法，但治疗的有效性将取决于这种干预措施如何改变该状态的演变。不幸的是，此过程不仅取决于该过程的动力学，而且是在干预时的系统状态决定的 - 这种状态在应用治疗之前很难确定即使不是不可能的状态。

可视化优化景观导致了数字优化的许多基本见解，并对优化技术进行了新的改进。但是，仅在少数狭窄的环境中生成了增强学习优化（“奖励表面”）的目标的可视化。这项工作首次介绍了27个最广泛使用的增强学习环境的奖励表面和相关的可视化。我们还探索了政策梯度方向上的奖励表面，并首次表明许多流行的强化学习环境经常出现“悬崖”（预期回报中突然下降）。我们证明，A2C经常将这些悬崖“脱落”到参数空间的低奖励区域，而PPO避免了它们，这证实了PPO对PPO的流行直觉，以改善以前的方法。我们还引入了一个高度可扩展的库，该库使研究人员将来可以轻松地生成这些可视化。我们的发现提供了新的直觉，以解释现代RL方法的成功和失败，我们的可视化构成了以新颖方式进行强化学习剂的几种失败模式。

实体联系面临着重大的挑战，例如多产的变化和普遍的歧义，特别是在具有无数实体的高价值领域。标准分类方法遭受注释瓶颈，无法有效处理看不见的实体。零拍实体链接已成为概括的方向，以概括新实体，但它仍然需要在所有实体的培训和规范描述期间提到示例，这两者都很少在维基百科外面可用。在本文中，我们通过利用易于提供的域知识来探索实体链接的知识丰富的自我监督（$ \ tt kriss $）。在培训中，它会使用域本体进行未标记的文本生成自我监控的提到示例，并使用对比学习列举一个上下文编码器。出于推理，它将自我监督的提到作为每个实体的原型，并通过将测试提及映射到最相似的原型来进行链接。我们的方法归入零拍摄和少量拍摄方法，并且可以轻松地包含实体说明和黄金如果可用的标签。使用Biomedicine作为案例研究，我们对跨越生物医学文献和临床票据的七个标准数据集进行了广泛的实验。不使用任何标记信息，我们的方法为400万UMLS实体提供$ \ TT Krissbert $，这是一个Uncer Intity Linker，它可以获得新的艺术状态，优先于先前的自我监督方法，高度为20多个绝对点。

Training of neural networks for automated diagnosis of pigmented skin lesions is hampered by the small size and lack of diversity of available datasets of dermatoscopic images. We tackle this problem by releasing the HAM10000 ("Human Against Machine with 10000 training images") dataset. We collected dermatoscopic images from different populations acquired and stored by different modalities. Given this diversity we had to apply different acquisition and cleaning methods and developed semi-automatic workflows utilizing specifically trained neural networks. The final dataset consists of 10015 dermatoscopic images which are released as a training set for academic machine learning purposes and are publicly available through the ISIC archive. This benchmark dataset can be used for machine learning and for comparisons with human experts. Cases include a representative collection of all important diagnostic categories in the realm of pigmented lesions. More than 50% of lesions have been confirmed by pathology, while the ground truth for the rest of the cases was either follow-up, expert consensus, or confirmation by in-vivo confocal microscopy. Design Type(s)database creation objective • data integration objective • image format conversion objective Measurement Type(s) skin lesions Technology Type(s) digital curation Factor Type(s) diagnosis • Diagnostic Procedure • age • biological sex • animal body part Sample Characteristic(s) Homo sapiens • skin of body

Neural Machine Translation (NMT) is an end-to-end learning approach for automated translation, with the potential to overcome many of the weaknesses of conventional phrase-based translation systems. Unfortunately, NMT systems are known to be computationally expensive both in training and in translation inference -sometimes prohibitively so in the case of very large data sets and large models. Several authors have also charged that NMT systems lack robustness, particularly when input sentences contain rare words. These issues have hindered NMT's use in practical deployments and services, where both accuracy and speed are essential. In this work, we present GNMT, Google's Neural Machine Translation system, which attempts to address many of these issues. Our model consists of a deep LSTM network with 8 encoder and 8 decoder layers using residual connections as well as attention connections from the decoder network to the encoder. To improve parallelism and therefore decrease training time, our attention mechanism connects the bottom layer of the decoder to the top layer of the encoder. To accelerate the final translation speed, we employ low-precision arithmetic during inference computations. To improve handling of rare words, we divide words into a limited set of common sub-word units ("wordpieces") for both input and output. This method provides a good balance between the flexibility of "character"-delimited models and the efficiency of "word"-delimited models, naturally handles translation of rare words, and ultimately improves the overall accuracy of the system. Our beam search technique employs a length-normalization procedure and uses a coverage penalty, which encourages generation of an output sentence that is most likely to cover all the words in the source sentence. To directly optimize the translation BLEU scores, we consider refining the models by using reinforcement learning, but we found that the improvement in the BLEU scores did not reflect in the human evaluation. On the WMT'14 English-to-French and English-to-German benchmarks, GNMT achieves competitive results to state-of-the-art. Using a human side-by-side evaluation on a set of isolated simple sentences, it reduces translation errors by an average of 60% compared to Google's phrase-based production system.