我们介绍了Sparrow,这是一个寻求信息的对话代理,与提示的语言模型基线相比,训练有素,更有帮助,正确和无害。我们使用从人类反馈中的强化学习来培训我们的模型,以帮助人类评估者判断代理人的行为。首先,为了使我们的代理人更有帮助和无害,我们将良好对话的要求分解为代理人应遵循的自然语言规则,并分别向评估者询问每个规则。我们证明,这种崩溃使我们能够收集对代理行为的更多针对性的人类判断,并允许更有效的规则条件奖励模型。其次,我们的代理商在收集对模型声明的偏好判决时提供了支持事实主张的来源的证据。对于事实问题,麻雀提供的证据支持了78%的时间。比基线比基线更享受麻雀,同时对人类的对抗性探测更具弹性,在探测时只有8%的时间违反了我们的规则。最后,我们进行了广泛的分析,表明尽管我们的模型学会遵守我们的规则,但它可以表现出分布偏见。
translated by 谷歌翻译
一阶逻辑的传统自动定理普通普及依赖于速度优化的搜索和许多手工制的启发式,旨在在各种域中工作。文献中的机器学习方法取决于这些传统的传统普通普通的自我或达到了可比性的比较短暂。在本文中,我们提出了一般的增量学习算法,用于培训域特定竞争员的一阶逻辑,而不是基本的给定 - 子算法,但使用学习的子句评分函数。子句被用作图表,并呈现给具有光谱特征的变压器网络。为了解决稀疏性和初步缺乏培训数据以及缺乏自然课程,我们适应后敏感经验重播到定理证明,即使没有找到证据。我们展示了这种方式培训的普通培训可以在TPTP数据集中匹配和有时会在证明的数量和质量方面超越TPTP数据集。
translated by 谷歌翻译
In this work we aim to solve a large collection of tasks using a single reinforcement learning agent with a single set of parameters. A key challenge is to handle the increased amount of data and extended training time. We have developed a new distributed agent IMPALA (Importance Weighted Actor-Learner Architecture) that not only uses resources more efficiently in singlemachine training but also scales to thousands of machines without sacrificing data efficiency or resource utilisation. We achieve stable learning at high throughput by combining decoupled acting and learning with a novel off-policy correction method called V-trace. We demonstrate the effectiveness of IMPALA for multi-task reinforcement learning on DMLab-30 (a set of 30 tasks from the DeepMind Lab environment (Beattie et al., 2016)) and Atari-57 (all available Atari games in Arcade Learning Environment (Bellemare et al., 2013a)). Our results show that IMPALA is able to achieve better performance than previous agents with less data, and crucially exhibits positive transfer between tasks as a result of its multi-task approach. The source code is publicly available at github.com/deepmind/scalable agent.
translated by 谷歌翻译
Scale-invariance is an open problem in many computer vision subfields. For example, object labels should remain constant across scales, yet model predictions diverge in many cases. This problem gets harder for tasks where the ground-truth labels change with the presentation scale. In image quality assessment (IQA), downsampling attenuates impairments, e.g., blurs or compression artifacts, which can positively affect the impression evoked in subjective studies. To accurately predict perceptual image quality, cross-resolution IQA methods must therefore account for resolution-dependent errors induced by model inadequacies as well as for the perceptual label shifts in the ground truth. We present the first study of its kind that disentangles and examines the two issues separately via KonX, a novel, carefully crafted cross-resolution IQA database. This paper contributes the following: 1. Through KonX, we provide empirical evidence of label shifts caused by changes in the presentation resolution. 2. We show that objective IQA methods have a scale bias, which reduces their predictive performance. 3. We propose a multi-scale and multi-column DNN architecture that improves performance over previous state-of-the-art IQA models for this task, including recent transformers. We thus both raise and address a novel research problem in image quality assessment.
translated by 谷歌翻译
Document images are a ubiquitous source of data where the text is organized in a complex hierarchical structure ranging from fine granularity (e.g., words), medium granularity (e.g., regions such as paragraphs or figures), to coarse granularity (e.g., the whole page). The spatial hierarchical relationships between content at different levels of granularity are crucial for document image understanding tasks. Existing methods learn features from either word-level or region-level but fail to consider both simultaneously. Word-level models are restricted by the fact that they originate from pure-text language models, which only encode the word-level context. In contrast, region-level models attempt to encode regions corresponding to paragraphs or text blocks into a single embedding, but they perform worse with additional word-level features. To deal with these issues, we propose MGDoc, a new multi-modal multi-granular pre-training framework that encodes page-level, region-level, and word-level information at the same time. MGDoc uses a unified text-visual encoder to obtain multi-modal features across different granularities, which makes it possible to project the multi-granular features into the same hyperspace. To model the region-word correlation, we design a cross-granular attention mechanism and specific pre-training tasks for our model to reinforce the model of learning the hierarchy between regions and words. Experiments demonstrate that our proposed model can learn better features that perform well across granularities and lead to improvements in downstream tasks.
translated by 谷歌翻译
在本文中,我们研究了视觉和热图像的性能和公平性,并将评估扩展到掩盖的合成图像。使用SeadyFace和Thermal掩码数据集,我们提出了一个过程来评估真实图像的公平性,并显示如何将同一过程应用于合成图像。随机猜测的人口统计差异为1.59,当识别性能提高到99.99 \%时,人口统计学差异为1.59。我们表明,固有的偏见数据集可以深深影响任何生物识别系统的公平性。偏见数据集的主要原因是由于数据收集过程而导致的类不平衡。为了解决不平衡的数据集,可以使用合成图像来增强样品的较少类,以生成更平衡的数据集,从而在训练机器学习系统时产生较小的偏见。对于支持生物特征的系统,公平性至关重要,而相关的公平,多样性和包容性(EDI)的相关概念非常适合生物识别技术公平性的概括,我们专注于3个最常见的人口统计组年龄,性别和种族。
translated by 谷歌翻译
连续的软件工程在许多领域已变得司空见惯。但是,在调节需要考虑其他问题的密集部门时,通常认为很难采用连续的开发方法,例如DevOps。在本文中,我们提出了一种将拉力请求用作设计控件的方法,并将这种方法应用于认证的医疗系统中的机器学习,这是一种新颖的技术,这是一种新颖的技术,旨在为机器学习系统增加解释性,作为监管审核跟踪。我们以前曾使用过一种工业系统来证明这种方法,以证明如何以连续的方式开发医疗系统。
translated by 谷歌翻译
DeNoising扩散模型代表了计算机视觉中最新的主题,在生成建模领域表现出了显着的结果。扩散模型是一个基于两个阶段的深层生成模型,一个正向扩散阶段和反向扩散阶段。在正向扩散阶段,通过添加高斯噪声,输入数据在几个步骤中逐渐受到干扰。在反向阶段,模型的任务是通过学习逐步逆转扩散过程来恢复原始输入数据。尽管已知的计算负担,即由于采样过程中涉及的步骤数量,扩散模型对生成样品的质量和多样性得到了广泛赞赏。在这项调查中,我们对视觉中应用的denoising扩散模型的文章进行了全面综述,包括该领域的理论和实际贡献。首先,我们识别并介绍了三个通用扩散建模框架,这些框架基于扩散概率模型,噪声调节得分网络和随机微分方程。我们进一步讨论了扩散模型与其他深层生成模型之间的关系,包括变异自动编码器,生成对抗网络,基于能量的模型,自回归模型和正常流量。然后,我们介绍了计算机视觉中应用的扩散模型的多角度分类。最后,我们说明了扩散模型的当前局限性,并设想了一些有趣的未来研究方向。
translated by 谷歌翻译
纳米大小的无人机具有探索未知和复杂环境的巨大潜力。它们的尺寸很小,使它们敏捷且安全地靠近人类,并使他们能够穿过狭窄的空间。但是,它们的尺寸很小和有效载荷限制了板载计算和传感的可能性,从而使完全自主的飞行极具挑战性。迈向完全自主权的第一步是可靠的避免障碍,这在通用的室内环境中被证明在技术上具有挑战性。当前的方法利用基于视觉或一维传感器来支持纳米无人机感知算法。这项工作为基于新颖的毫米尺寸64像素多区域飞行时间(TOF)传感器和通用的无模型控制策略提供了轻巧的避免障碍系统。报告的现场测试基于Crazyflie 2.1,该测试由定制的多区TOF甲板扩展,总质量为35克。该算法仅使用0.3%的车载处理能力(210US执行时间),帧速率为15fps,为许多未来应用提供了绝佳的基础。运行提出的感知系统(包括抬起和操作传感器)所需的总无人机功率不到10%。在通用且以前未开发的室内环境中,提出的自动纳米大小无人机以0.5m/s的速度达到100%可靠性。所提出的系统释放出具有广泛数据集的开源,包括TOF和灰度摄像头数据,并与运动捕获中的无人机位置地面真相结合在一起。
translated by 谷歌翻译
无监督的视觉表示学习提供了一个机会,可以利用大型无标记轨迹的大型语料库形成有用的视觉表示,这可以使强化学习(RL)算法的培训受益。但是,评估此类表示的适应性需要培训RL算法,该算法在计算上是密集型且具有较高的差异结果。为了减轻此问题,我们为无监督的RL表示方案设计了一个评估协议,其差异较低,计算成本降低了600倍。受愿景社区的启发,我们提出了两个线性探测任务:预测在给定状态下观察到的奖励,并预测特定状态下专家的行动。这两个任务通常适用于许多RL域,我们通过严格的实验表明,它们与Atari100k基准的实际下游控制性能密切相关。这提供了一种更好的方法,可以探索预处理算法的空间,而无需为每个设置运行RL评估。利用这一框架,我们进一步改善了RL的现有自学学习(SSL)食谱,突出了前向模型的重要性,视觉骨架的大小以及无监督目标的精确配方。
translated by 谷歌翻译