使用变压器模型，多语言神经机器的翻译一直显示出巨大的成功。部署这些模型是具有挑战性的，因为它们通常需要各种语言的大词汇（词汇）尺寸。这限制了在上一个词汇投影层中预测输出令牌的速度。为了减轻这些挑战，本文提出了一种通过聚类的快速词汇投影方法，该方法可用于GPU上的多语言变压器。首先，我们脱机将词汇搜索空间分为不同的结合群，鉴于解码器输出的隐藏上下文向量，这导致词汇投影的词汇列要小得多。其次，在推理时，提出的方法预测了词汇投影中隐藏上下文向量的簇和候选候选代币。本文还包括对在多语言环境中构建这些群集的不同方式的分析。我们的结果表明，FLOAT16 GPU推断中的端到端速度增长高达25％，同时保持BLEU得分并略有增加记忆成本。所提出的方法将词汇投影步骤加速自身最多2.6倍。我们还进行了广泛的人类评估，以验证所提出的方法保留了原始模型的翻译质量。

本文提出了一种简单而有效的方法，可以改善两种情况下的直接（x-to-y）翻译：零射击和直接数据时。我们将编码器和解码器的输入令牌修改为包括源和目标语言的信号。我们在从头开始训练或使用拟议的设置对验证模型进行填充时显示出绩效增长。在实验中，根据检查点选择标准，我们的方法在内部数据集上显示了近10.0个BLEU点的增益。在WMT评估活动中，从英语性能提高了4.17和2.87 BLEU点，在零射击设置和直接数据可用于培训时。而X-to-y在零射基线上提高了1.29 BLEU，而在多到许多基线上提高了0.44。在低资源设置中，我们在X-TO-Y域数据上进行填充时会看到1.5〜1.7点的改善。

本文介绍了我们提交给WMT21共享新闻翻译任务的受限轨道。我们专注于三个相对低的资源语言对孟加拉，从印地语，英语往返Hausa，以及来自Zulu的Xhosa。为了克服相对低行数据的限制，我们使用采用并行和单晶体数据的多任务目标训练多语言模型。此外，我们使用后退转换增强数据。我们还培养了一种双语模型，包括后退转换和知识蒸馏，然后使用序列到序列映射来组合两种模型。我们看到迄今为止英语和来自Hausa的Bleu Point的相对收益约为70％，以及与双语基线相比，孟加拉和从Zulu的孟加拉和从Zulu的相对改善约25％。

The field of autonomous mobile robots has undergone dramatic advancements over the past decades. Despite achieving important milestones, several challenges are yet to be addressed. Aggregating the achievements of the robotic community as survey papers is vital to keep the track of current state-of-the-art and the challenges that must be tackled in the future. This paper tries to provide a comprehensive review of autonomous mobile robots covering topics such as sensor types, mobile robot platforms, simulation tools, path planning and following, sensor fusion methods, obstacle avoidance, and SLAM. The urge to present a survey paper is twofold. First, autonomous navigation field evolves fast so writing survey papers regularly is crucial to keep the research community well-aware of the current status of this field. Second, deep learning methods have revolutionized many fields including autonomous navigation. Therefore, it is necessary to give an appropriate treatment of the role of deep learning in autonomous navigation as well which is covered in this paper. Future works and research gaps will also be discussed.

We introduce a machine-learning (ML)-based weather simulator--called "GraphCast"--which outperforms the most accurate deterministic operational medium-range weather forecasting system in the world, as well as all previous ML baselines. GraphCast is an autoregressive model, based on graph neural networks and a novel high-resolution multi-scale mesh representation, which we trained on historical weather data from the European Centre for Medium-Range Weather Forecasts (ECMWF)'s ERA5 reanalysis archive. It can make 10-day forecasts, at 6-hour time intervals, of five surface variables and six atmospheric variables, each at 37 vertical pressure levels, on a 0.25-degree latitude-longitude grid, which corresponds to roughly 25 x 25 kilometer resolution at the equator. Our results show GraphCast is more accurate than ECMWF's deterministic operational forecasting system, HRES, on 90.0% of the 2760 variable and lead time combinations we evaluated. GraphCast also outperforms the most accurate previous ML-based weather forecasting model on 99.2% of the 252 targets it reported. GraphCast can generate a 10-day forecast (35 gigabytes of data) in under 60 seconds on Cloud TPU v4 hardware. Unlike traditional forecasting methods, ML-based forecasting scales well with data: by training on bigger, higher quality, and more recent data, the skill of the forecasts can improve. Together these results represent a key step forward in complementing and improving weather modeling with ML, open new opportunities for fast, accurate forecasting, and help realize the promise of ML-based simulation in the physical sciences.

Low Earth Orbit (LEO) constellations, each comprising a large number of satellites, have become a new source of big data "from the sky". Downloading such data to a ground station (GS) for big data analytics demands very high bandwidth and involves large propagation delays. Federated Learning (FL) offers a promising solution because it allows data to stay in-situ (never leaving satellites) and it only needs to transmit machine learning model parameters (trained on the satellites' data). However, the conventional, synchronous FL process can take several days to train a single FL model in the context of satellite communication (Satcom), due to a bottleneck caused by straggler satellites. In this paper, we propose an asynchronous FL framework for LEO constellations called AsyncFLEO to improve FL efficiency in Satcom. Not only does AsynFLEO address the bottleneck (idle waiting) in synchronous FL, but it also solves the issue of model staleness caused by straggler satellites. AsyncFLEO utilizes high-altitude platforms (HAPs) positioned "in the sky" as parameter servers, and consists of three technical components: (1) a ring-of-stars communication topology, (2) a model propagation algorithm, and (3) a model aggregation algorithm with satellite grouping and staleness discounting. Our extensive evaluation with both IID and non-IID data shows that AsyncFLEO outperforms the state of the art by a large margin, cutting down convergence delay by 22 times and increasing accuracy by 40%.

A Complete Computer vision system can be divided into two main categories: detection and classification. The Lane detection algorithm is a part of the computer vision detection category and has been applied in autonomous driving and smart vehicle systems. The lane detection system is responsible for lane marking in a complex road environment. At the same time, lane detection plays a crucial role in the warning system for a car when departs the lane. The implemented lane detection algorithm is mainly divided into two steps: edge detection and line detection. In this paper, we will compare the state-of-the-art implementation performance obtained with both FPGA and GPU to evaluate the trade-off for latency, power consumption, and utilization. Our comparison emphasises the advantages and disadvantages of the two systems.

Automatic segmentation is essential for the brain tumor diagnosis, disease prognosis, and follow-up therapy of patients with gliomas. Still, accurate detection of gliomas and their sub-regions in multimodal MRI is very challenging due to the variety of scanners and imaging protocols. Over the last years, the BraTS Challenge has provided a large number of multi-institutional MRI scans as a benchmark for glioma segmentation algorithms. This paper describes our contribution to the BraTS 2022 Continuous Evaluation challenge. We propose a new ensemble of multiple deep learning frameworks namely, DeepSeg, nnU-Net, and DeepSCAN for automatic glioma boundaries detection in pre-operative MRI. It is worth noting that our ensemble models took first place in the final evaluation on the BraTS testing dataset with Dice scores of 0.9294, 0.8788, and 0.8803, and Hausdorf distance of 5.23, 13.54, and 12.05, for the whole tumor, tumor core, and enhancing tumor, respectively. Furthermore, the proposed ensemble method ranked first in the final ranking on another unseen test dataset, namely Sub-Saharan Africa dataset, achieving mean Dice scores of 0.9737, 0.9593, and 0.9022, and HD95 of 2.66, 1.72, 3.32 for the whole tumor, tumor core, and enhancing tumor, respectively. The docker image for the winning submission is publicly available at (https://hub.docker.com/r/razeineldin/camed22).

The number of international benchmarking competitions is steadily increasing in various fields of machine learning (ML) research and practice. So far, however, little is known about the common practice as well as bottlenecks faced by the community in tackling the research questions posed. To shed light on the status quo of algorithm development in the specific field of biomedical imaging analysis, we designed an international survey that was issued to all participants of challenges conducted in conjunction with the IEEE ISBI 2021 and MICCAI 2021 conferences (80 competitions in total). The survey covered participants' expertise and working environments, their chosen strategies, as well as algorithm characteristics. A median of 72% challenge participants took part in the survey. According to our results, knowledge exchange was the primary incentive (70%) for participation, while the reception of prize money played only a minor role (16%). While a median of 80 working hours was spent on method development, a large portion of participants stated that they did not have enough time for method development (32%). 25% perceived the infrastructure to be a bottleneck. Overall, 94% of all solutions were deep learning-based. Of these, 84% were based on standard architectures. 43% of the respondents reported that the data samples (e.g., images) were too large to be processed at once. This was most commonly addressed by patch-based training (69%), downsampling (37%), and solving 3D analysis tasks as a series of 2D tasks. K-fold cross-validation on the training set was performed by only 37% of the participants and only 50% of the participants performed ensembling based on multiple identical models (61%) or heterogeneous models (39%). 48% of the respondents applied postprocessing steps.

With an increasing amount of data in the art world, discovering artists and artworks suitable to collectors' tastes becomes a challenge. It is no longer enough to use visual information, as contextual information about the artist has become just as important in contemporary art. In this work, we present a generic Natural Language Processing framework (called ArtLM) to discover the connections among contemporary artists based on their biographies. In this approach, we first continue to pre-train the existing general English language models with a large amount of unlabelled art-related data. We then fine-tune this new pre-trained model with our biography pair dataset manually annotated by a team of professionals in the art industry. With extensive experiments, we demonstrate that our ArtLM achieves 85.6% accuracy and 84.0% F1 score and outperforms other baseline models. We also provide a visualisation and a qualitative analysis of the artist network built from ArtLM's outputs.