As Artificial and Robotic Systems are increasingly deployed and relied upon for real-world applications, it is important that they exhibit the ability to continually learn and adapt in dynamically-changing environments, becoming Lifelong Learning Machines. Continual/lifelong learning (LL) involves minimizing catastrophic forgetting of old tasks while maximizing a model's capability to learn new tasks. This paper addresses the challenging lifelong reinforcement learning (L2RL) setting. Pushing the state-of-the-art forward in L2RL and making L2RL useful for practical applications requires more than developing individual L2RL algorithms; it requires making progress at the systems-level, especially research into the non-trivial problem of how to integrate multiple L2RL algorithms into a common framework. In this paper, we introduce the Lifelong Reinforcement Learning Components Framework (L2RLCF), which standardizes L2RL systems and assimilates different continual learning components (each addressing different aspects of the lifelong learning problem) into a unified system. As an instantiation of L2RLCF, we develop a standard API allowing easy integration of novel lifelong learning components. We describe a case study that demonstrates how multiple independently-developed LL components can be integrated into a single realized system. We also introduce an evaluation environment in order to measure the effect of combining various system components. Our evaluation environment employs different LL scenarios (sequences of tasks) consisting of Starcraft-2 minigames and allows for the fair, comprehensive, and quantitative comparison of different combinations of components within a challenging common evaluation environment.
translated by 谷歌翻译
应对深层终身强化学习(LRL)挑战的一种方法是仔细管理代理商的学习经验,以学习(不忘记)并建立内部元模型(任务,环境,代理商和世界)。生成重播(GR)是一种以生物学启发的重播机制,可以通过从内部生成模型中绘制的自标记示例来增强学习经验,该模型随着时间的推移而更新。在本文中,我们提出了一个满足两个Desiderata的GR版本:(a)使用深RL学习的策略的潜在策略的内省密度建模,以及(b)无模型的端到端学习。在这项工作中,我们研究了三个无模型GR的深度学习体系结构。我们在三种不同的情况下评估了我们提出的算法,其中包括来自Starcraft2和Minigrid域的任务。我们报告了几个关键发现,显示了设计选择对定量指标的影响,包括转移学习,对看不见的任务的概括,任务更改后的快速适应,与任务专家相当的绩效以及最小化灾难性遗忘。我们观察到我们的GR可以防止从深层批评剂的潜在矢量空间中的特征映射中漂移。我们还显示了既定的终身学习指标的改进。我们发现,当与重播缓冲液和生成的重播缓冲液结合使用时,需要引入一个小的随机重放缓冲液,以显着提高训练的稳定性。总体而言,我们发现“隐藏的重播”(一种众所周知的班级入学分类体系结构)是最有前途的方法,它推动了LRL的GR中最新的方法。
translated by 谷歌翻译
在本文中,我们介绍了战术边缘(水合物)的高维可重构分析,使用低S型嵌入式硬件可以在利用非MAC的边缘进行实时重新配置(不含浮点多裂动作)(无浮点多裂动作)(深神经网络)( DNN)结合了高度(HD)计算加速器。我们描述了算法,经过训练的量化模型生成以及功能提取器的模拟性能,不含多重蓄能的供您喂养基于高维逻辑的分类器。然后,我们展示了性能如何随着超数的数量而增加。我们将与传统DNN相比,描述已实现的低压FPGA硬件和嵌入式软件系统,并详细介绍实现的硬件加速器。我们讨论了测量的系统延迟和功率,由于使用可学习的量化和高清计算而引起的噪声稳健性,用于视频活动分类任务的实际和模拟系统性能以及在同一数据集上进行重新配置的演示。我们表明,仅使用梯度下降反向传播(无梯度)的馈电HD分类器(无梯度),可以通过使用几乎没有射击的新课程来实现现场的可重构性。最初的工作使用了LRCN DNN,目前已扩展到使用具有改进性能的两流DNN。
translated by 谷歌翻译
我们研究了如何使用来自生物视觉的扫视机制来使深层神经网络更有效地用于分类和对象检测问题。我们提出的方法是基于注意力驱动的视觉处理和扫视的思想,由注意力影响的微型眼动。我们通过分析进行实验:i)不同的深神经网络(DNN)特征提取器的鲁棒性对部分感知图像进行图像分类和对象检测,以及ii)acccades在掩盖图像贴片中用于图像分类和对象跟踪的效用。在几个数据集(CIFAR-10,DAVSOD,MSCOCO和MOT17)上进行了卷积网(RESNET-18)和基于变压器模型(VIT,DETR,TRANSTRACK)的实验。我们的实验显示了通过学习与最先进的DNN一起用于分类,检测和跟踪任务时模仿人类扫视的智能数据减少。我们观察到分类和检测任务的性能下降最少,而仅使用约30 \%的原始传感器数据。我们讨论扫视机制如何通过``像素''处理来为硬件设计提供信息。
translated by 谷歌翻译
我们介绍Samanantar,是最大的公开可用的并行Corpora Collection,用于指示语言。该集合中的英语和11个上线语言之间总共包含4970万句对(来自两种语言系列)。具体而言,我们从现有的公共可用并行基层编译1240万句对,另外,从网络上挖掘3740万句对,导致4倍增加。我们通过组合许多语料库,工具和方法来挖掘网站的并行句子:(a)Web爬行单格式语料库,(b)文档OCR,用于从扫描的文档中提取句子,(c)用于对齐句子的多语言表示模型,以及(d)近似最近的邻居搜索搜索大量句子。人类评估新矿业的Corpora的样本验证了11种语言的高质量平行句子。此外,我们使用英语作为枢轴语言,从英式并行语料库中提取所有55个指示语言对之间的834百万句子对。我们培训了跨越Samanantar上所有这些语言的多语种NMT模型,这在公开可用的基准上表现出现有的模型和基准,例如弗洛雷斯,建立萨曼塔尔的效用。我们的数据和模型可在Https://indicnlp.ai4bharat.org/samanantar/上公开提供,我们希望他们能够帮助推进NMT和Multibingual NLP的研究。
translated by 谷歌翻译
Climate change, population growth, and water scarcity present unprecedented challenges for agriculture. This project aims to forecast soil moisture using domain knowledge and machine learning for crop management decisions that enable sustainable farming. Traditional methods for predicting hydrological response features require significant computational time and expertise. Recent work has implemented machine learning models as a tool for forecasting hydrological response features, but these models neglect a crucial component of traditional hydrological modeling that spatially close units can have vastly different hydrological responses. In traditional hydrological modeling, units with similar hydrological properties are grouped together and share model parameters regardless of their spatial proximity. Inspired by this domain knowledge, we have constructed a novel domain-inspired temporal graph convolution neural network. Our approach involves clustering units based on time-varying hydrological properties, constructing graph topologies for each cluster, and forecasting soil moisture using graph convolutions and a gated recurrent neural network. We have trained, validated, and tested our method on field-scale time series data consisting of approximately 99,000 hydrological response units spanning 40 years in a case study in northeastern United States. Comparison with existing models illustrates the effectiveness of using domain-inspired clustering with time series graph neural networks. The framework is being deployed as part of a pro bono social impact program. The trained models are being deployed on small-holding farms in central Texas.
translated by 谷歌翻译
In this work, we present an evaluation of smaller BLOOM model variants (350m/560m and 1b3/1b7) on various natural language processing tasks. This includes GLUE - language understanding, prompt-based zero-shot and few-shot text classification and extraction, question answering, prompt-based text generation, and multi-lingual text classification to understand model strengths/weaknesses and behavior. Empirical results show that BLOOM variants under-perform on all GLUE tasks (except WNLI), question-answering, and text generation. The variants bloom for WNLI, with an accuracy of 56.3%, and for prompt-based few-shot text extraction on MIT Movies and ATIS datasets. The BLOOM variants on average have 7% greater accuracy over GPT-2 and GPT-Neo models on Director and Airline Name extraction from MIT Movies and ATIS datasets, respectively.
translated by 谷歌翻译
Identification of named entities from legal texts is an essential building block for developing other legal Artificial Intelligence applications. Named Entities in legal texts are slightly different and more fine-grained than commonly used named entities like Person, Organization, Location etc. In this paper, we introduce a new corpus of 46545 annotated legal named entities mapped to 14 legal entity types. The Baseline model for extracting legal named entities from judgment text is also developed.
translated by 谷歌翻译
蚊子传播的疾病(MBD),例如登革热病毒,基孔肯雅病毒和西尼罗河病毒,每年在全球造成超过100万人死亡。由于许多这样的疾病都被伊蚊和库氏蚊子传播,因此跟踪这些幼虫对于缓解MBD的传播至关重要。即使公民科学成长并获得了较大的蚊子图像数据集,蚊子图像的手动注释变得越来越耗时且效率低下。先前的研究使用计算机视觉识别蚊子物种,卷积神经网络(CNN)已成为图像分类的事实。但是,这些模型通常需要大量的计算资源。这项研究介绍了视觉变压器(VIT)在比较研究中的应用,以改善伊蚊和库尔克斯幼虫的图像分类。在蚊子幼虫图像数据上对两个VIT模型,Vit-Base和CVT-13以及两个CNN模型进行了RESNET-18和CORVNEXT的培训,并比较确定最有效的模型,以将蚊子幼虫区分为AEDES或CULEX。测试表明,Convnext获得了所有分类指标的最大值,证明了其对蚊子幼虫分类的生存能力。基于这些结果,未来的研究包括通过结合CNN和Transformer架构元素来创建专门为蚊子幼虫分类设计的模型。
translated by 谷歌翻译
场景变化检测(SCD)是一项关键的感知任务,通过比较在不同时间捕获的场景来确定变化。 SCD由于嘈杂的照明,季节性变化和两次观点的透视差异而具有挑战性。基于深度神经网络的解决方案需要大量的注释数据,这些数据乏味而昂贵。另一方面,从大型数据集中传输学习会导致域移动。为了应对这些挑战,我们提出了一种新颖的\ textit {差异自我监督预审(DSP)}方法,该方法使用特征差异来学习与变化区域相对应的歧视性表示,同时通过跨视图来实现时间不变性来解决嘈杂的变化。我们对SCD数据集的实验结果证明了我们方法的有效性,特别是在摄像机观点和照明条件下的差异。与使用超过一百万个标记的图像的自我监督的Barlow双胞胎和标准图像预处理相比,DSP可以超过它而无需使用任何其他数据。我们的结果还证明了DSP对自然腐败,分配转移和学习有限的数据的鲁棒性。
translated by 谷歌翻译