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.
translated by 谷歌翻译
In this paper, we propose a novel architecture, the Enhanced Interactive Transformer (EIT), to address the issue of head degradation in self-attention mechanisms. Our approach replaces the traditional multi-head self-attention mechanism with the Enhanced Multi-Head Attention (EMHA) mechanism, which relaxes the one-to-one mapping constraint among queries and keys, allowing each query to attend to multiple keys. Furthermore, we introduce two interaction models, Inner-Subspace Interaction and Cross-Subspace Interaction, to fully utilize the many-to-many mapping capabilities of EMHA. Extensive experiments on a wide range of tasks (e.g. machine translation, abstractive summarization, grammar correction, language modelling and brain disease automatic diagnosis) show its superiority with a very modest increase in model size.
translated by 谷歌翻译
We present a method for introducing a text encoder into pre-trained end-to-end speech translation systems. It enhances the ability of adapting one modality (i.e., source-language speech) to another (i.e., source-language text). Thus, the speech translation model can learn from both unlabeled and labeled data, especially when the source-language text data is abundant. Beyond this, we present a denoising method to build a robust text encoder that can deal with both normal and noisy text data. Our system sets new state-of-the-arts on the MuST-C En-De, En-Fr, and LibriSpeech En-Fr tasks.
translated by 谷歌翻译
高分辨率卫星图像可以为土地覆盖分类提供丰富的详细空间信息,这对于研究复杂的建筑环境尤为重要。但是,由于覆盖范围复杂的覆盖模式,昂贵的训练样品收集以及卫星图像的严重分布变化,很少有研究应用高分辨率图像来大规模详细类别的覆盖地图。为了填补这一空白,我们提出了一个大规模的土地盖数据集,即五亿像素。它包含超过50亿个标记的像素,这些像素由150个高分辨率Gaofen-2(4 M)卫星图像,在24类系统中注释,涵盖人工结构,农业和自然阶层。此外,我们提出了一种基于深度学习的无监督域适应方法,该方法可以转移在标记的数据集(称为源域)上训练的分类模型,以获取大型土地覆盖映射的无标记数据(称为目标域) 。具体而言,我们采用动态伪标签分配和班级平衡策略来介绍一个端到端的暹罗网络,以执行自适应领域联合学习。为了验证我们的数据集的普遍性以及在不同的传感器和不同地理区域中提出的方法,我们对中国的五个大城市和其他五个亚洲国家的五个城市进行了土地覆盖地图,以下情况下使用:Planetscope(3 m),Gaofen-1,Gaofen-1 (8 m)和Sentinel-2(10 m)卫星图像。在总研究区域为60,000平方公里,即使输入图像完全未标记,实验也显示出令人鼓舞的结果。拟议的方法接受了5亿像素数据集的培训,可实现在整个中国和其他亚洲国家的高质量和详细的土地覆盖地图。
translated by 谷歌翻译
尽管深度神经网络(DNNS)在音频分类任务中取得了巨大的成功,但它们的不确定性校准仍未得到探索。当它确定其预测时,应进行良好的模型应准确,并表明何时可能不准确。在这项工作中,我们研究了深度音频分类器的不确定性校准。特别是,我们从经验上研究了流行校准方法的性能:(i)蒙特卡洛辍学方法,(ii)集合,(iii)局灶性损失和(iv)光谱范围差异高斯工艺(SNGP),在音频分类数据集上。为此,我们评估了(I-IV),以应对环境声音和音乐流派分类的任务。结果表明,未校准的深度音频分类器可能过于自信,并且SNGP在本文的两个数据集中表现最好,并且非常有效。
translated by 谷歌翻译
多尺度特征层次结构已在计算机视觉区域的成功中得到了见证。这进一步激发了研究人员设计自然语言处理的多尺度变压器,主要是基于自我发项机制。例如,限制跨头部的接收场或通过卷积提取局部细粒度特征。但是,大多数现有作品都直接建模了本地功能,但忽略了单词边界信息。这导致了缺乏解释性的多余和模棱两可的注意力分布。在这项工作中,我们在不同的语言单元中定义了这些量表,包括子字,单词和短语。我们通过基于单词边界信息和短语级别的先验知识之间建立量表之间的关系来构建多尺度变压器模型。提出的\ textbf {u} niversal \ textbf {m} ulti \ textbf {s} cale \ textbf {t} ransformer,即在两个序列生成任务上评估。值得注意的是,它在几个测试组上的强大基线上产生了一致的性能,而无需牺牲效率。
translated by 谷歌翻译
稀疏培训是一种自然的想法,可以加速深度神经网络的训练速度,并节省内存使用,特别是因为大型现代神经网络被显着过度参数化。然而,大多数现有方法在实践中无法实现这一目标,因为先前方法采用的基于链规则的梯度(W.R.T.结构参数)估计。至少在向后传播步骤中至少需要密集的计算。本文通过提出具有完全稀疏的前后通行证的有效稀疏训练方法来解决这个问题。我们首先在全球稀疏限制下将培训过程制定为连续最小化问题。然后,我们将优化过程分为两个步骤,对应于权重更新和结构参数更新。对于前一步,我们使用传统的链规则,这可以通过利用稀疏结构来稀疏。对于后一步,而不是使用基于链规则的梯度估计器,如现有方法中,我们提出了一个方差减少的策略梯度估计器,这只需要两个向前通过而不向后传播,从而实现完全稀疏的训练。我们证明了我们渐变估计器的差异是界定的。对现实世界数据集的广泛实验结果表明,与以前的方法相比,我们的算法在加速训练过程中更有效,速度快到速度更快。
translated by 谷歌翻译
随着人工智能(AI)的迅速发展,可以预见的是,动态模拟器和AI的整合将大大提高对未来电力系统的动态分析的准确性和效率。为了探索电力系统动态模拟的交互机制和AI的相互作用机制,提出了面向AI的动力系统动态模拟器的一般设计,该设计由具有神经网络支持性的高性能模拟器和灵活的外部和内部应用程序编程接口(APIS)组成(APIS(APIS) )。在API的支持下,模拟辅助AI和AI辅助模拟形成了功率系统动态模拟与AI之间的全面交互机制。该设计的原型由基于高效的机电模拟器实施并公开。该原型的测试是在四种情况下进行的,包括样本生成,基于AI的稳定性预测,数据驱动的动态组件建模和AI AIDED稳定性控制,这证明了设计和实施的有效性,灵活性和效率面向AI的动力系统动态模拟器。
translated by 谷歌翻译
注入人类知识是加速加强学习(RL)的有效途径。但是,这些方法是缺乏缺陷的。本文介绍了我们发现的抽象前瞻性模型(思想游戏(TG))与转移学习(TL)相结合是有效的方式。我们将星际争霸II作为我们的学习环境。在设计的TG的帮助下,该代理可以在64x64地图上学习99%的速率,在一个商业机器中仅使用1.08小时的1级内置AI。我们还表明TG方法并不像被认为是限制性的。它可以使用粗略设计的TGS,并且在环境变化时也可以很有用。与以前的基于模型的RL相比,我们显示TG更有效。我们还提出了一种TG假设,其赋予TG不同保真度水平的影响。对于具有不等状态和行动空间的真实游戏,我们提出了一种新颖的XFRNET,其中有用性在验证有用性,同时达到欺骗级别-10 AI的90%的赢利。我们认为TG方法可能会在利用人类知识的进一步研究中进一步研究。
translated by 谷歌翻译
Weakly-supervised object localization aims to indicate the category as well as the scope of an object in an image given only the image-level labels. Most of the existing works are based on Class Activation Mapping (CAM) and endeavor to enlarge the discriminative area inside the activation map to perceive the whole object, yet ignore the co-occurrence confounder of the object and context (e.g., fish and water), which makes the model inspection hard to distinguish object boundaries. Besides, the use of CAM also brings a dilemma problem that the classification and localization always suffer from a performance gap and can not reach their highest accuracy simultaneously. In this paper, we propose a casual knowledge distillation method, dubbed KD-CI-CAM, to address these two under-explored issues in one go. More specifically, we tackle the co-occurrence context confounder problem via causal intervention (CI), which explores the causalities among image features, contexts, and categories to eliminate the biased object-context entanglement in the class activation maps. Based on the de-biased object feature, we additionally propose a multi-teacher causal distillation framework to balance the absorption of classification knowledge and localization knowledge during model training. Extensive experiments on several benchmarks demonstrate the effectiveness of KD-CI-CAM in learning clear object boundaries from confounding contexts and addressing the dilemma problem between classification and localization performance.
translated by 谷歌翻译