Several self-supervised representation learning methods have been proposed for reinforcement learning (RL) with rich observations. For real-world applications of RL, recovering underlying latent states is crucial, particularly when sensory inputs contain irrelevant and exogenous information. In this work, we study how information bottlenecks can be used to construct latent states efficiently in the presence of task-irrelevant information. We propose architectures that utilize variational and discrete information bottlenecks, coined as RepDIB, to learn structured factorized representations. Exploiting the expressiveness bought by factorized representations, we introduce a simple, yet effective, bottleneck that can be integrated with any existing self-supervised objective for RL. We demonstrate this across several online and offline RL benchmarks, along with a real robot arm task, where we find that compressed representations with RepDIB can lead to strong performance improvements, as the learned bottlenecks help predict only the relevant state while ignoring irrelevant information.
translated by 谷歌翻译
Despite their impressive performance on diverse tasks, large language models (LMs) still struggle with tasks requiring rich world knowledge, implying the limitations of relying solely on their parameters to encode a wealth of world knowledge. This paper aims to understand LMs' strengths and limitations in memorizing factual knowledge, by conducting large-scale knowledge probing experiments of 10 models and 4 augmentation methods on PopQA, our new open-domain QA dataset with 14k questions. We find that LMs struggle with less popular factual knowledge, and that scaling fails to appreciably improve memorization of factual knowledge in the tail. We then show that retrieval-augmented LMs largely outperform orders of magnitude larger LMs, while unassisted LMs remain competitive in questions about high-popularity entities. Based on those findings, we devise a simple, yet effective, method for powerful and efficient retrieval-augmented LMs, which retrieves non-parametric memories only when necessary. Experimental results show that this significantly improves models' performance while reducing the inference costs.
translated by 谷歌翻译
Computational notebooks, such as Jupyter notebooks, are interactive computing environments that are ubiquitous among data scientists to perform data wrangling and analytic tasks. To measure the performance of AI pair programmers that automatically synthesize programs for those tasks given natural language (NL) intents from users, we build ARCADE, a benchmark of 1082 code generation problems using the pandas data analysis framework in data science notebooks. ARCADE features multiple rounds of NL-to-code problems from the same notebook. It requires a model to understand rich multi-modal contexts, such as existing notebook cells and their execution states as well as previous turns of interaction. To establish a strong baseline on this challenging task, we develop PaChiNCo, a 62B code language model (LM) for Python computational notebooks, which significantly outperforms public code LMs. Finally, we explore few-shot prompting strategies to elicit better code with step-by-step decomposition and NL explanation, showing the potential to improve the diversity and explainability of model predictions.
translated by 谷歌翻译
最近,致力于通过现代机器学习方法预测脑部疾病的最新神经影像学研究通常包括单一模态并依靠监督的过度参数化模型。但是,单一模态仅提供了高度复杂的大脑的有限视图。至关重要的是,临床环境中的有监督模型缺乏用于培训的准确诊断标签。粗标签不会捕获脑疾病表型的长尾谱,这导致模型的普遍性丧失,从而使它们在诊断环境中的有用程度降低。这项工作提出了一个新型的多尺度协调框架,用于从多模式神经影像数据中学习多个表示。我们提出了一般的归纳偏见分类法,以捕获多模式自学融合中的独特和联合信息。分类法构成了一个无解码器模型的家族,具有降低的计算复杂性,并捕获多模式输入的本地和全局表示之间的多尺度关系。我们使用各种阿尔茨海默氏病表型中使用功能和结构磁共振成像(MRI)数据对分类法进行了全面评估,并表明自我监督模型揭示了与疾病相关的大脑区域和多模态链接,而无需在预先访问PRE-PRE-the PRE-the PRE-the PRE-the PRE-PRECTEN NICKES NOCKER NOCKER NOCKER NOCKER NOCKER NOCE访问。训练。拟议的多模式自学学习的学习能够表现出两种模式的分类表现。伴随的丰富而灵活的无监督的深度学习框架捕获了复杂的多模式关系,并提供了符合或超过更狭窄的监督分类分析的预测性能。我们提供了详尽的定量证据,表明该框架如何显着提高我们对复杂脑部疾病中缺失的联系的搜索。
translated by 谷歌翻译
机器学习(ML)可解释性技术可以揭示数据中的不良模式,这些模型模型开发以做出预测 - 一旦部署就会​​造成危害。但是,如何采取行动解决这些模式并不总是很清楚。在ML与人类计算机互动研究人员,医师和数据科学家之间的合作中,我们开发了GAM Changer,这是第一个互动系统,可帮助域专家和数据科学家轻松,负责任地编辑通用的添加剂模型(GAM)和修复有问题的模式。借助新颖的交互技术,我们的工具将可解释性置于行动中 - 使用户能够分析,验证和使模型行为与知识和价值相结合。医师已经开始使用我们的工具来调查和修复肺炎和败血症的风险预测模型,以及在不同领域工作的7位数据科学家的评估突出显示我们的工具易于使用,满足他们的模型编辑需求,并适合他们当前的工作流程。我们的工具以现代网络技术为基础,在用户的网络浏览器或计算笔记本电脑中本地运行,从而降低了使用的障碍。 GAM Changer可在以下公共演示链接中获得:https://interpret.ml/gam-changer。
translated by 谷歌翻译
来自科幻小说的普通愿景是机器人将有一天居住在我们的物理空间中,感知世界,才能协助我们的物理劳动力,并通过自然语言与我们沟通。在这里,我们研究如何使用虚拟环境的简化设计如何与人类自然交互的人工代理。我们表明,与自我监督学习的模拟世界中的人类交互的模仿学习足以产生我们称之为MIA的多模式互动剂,这成功与非对抗人类互动75%的时间。我们进一步确定了提高性能的架构和算法技术,例如分层动作选择。完全,我们的结果表明,模仿多模态,实时人类行为可以提供具有丰富的行为的富含性的令人生意的和令人惊讶的有效手段,然后可以为特定目的进行微调,从而铺设基础用于培训互动机器人或数字助理的能力。可以在https://youtu.be/zfgrif7my找到MIA的行为的视频
translated by 谷歌翻译
最近在可解释的机器学习中的进展(ML)研究表明,模型利用数据中的不良模式来进行预测,这可能导致部署危害。但是,尚不清楚我们如何解决这些模型。我们介绍了我们正在进行的工作,游戏改变者,一个开源交互式系统,以帮助数据科学家和领域专家轻松且负责任地编辑其广义添加剂模型(Gams)。通过新颖的可视化技术,我们的工具将可解释性投入到行动 - 使人类用户能够分析,验证和对齐模型行为与他们的知识和价值。使用现代Web技术建造,我们的工具在用户的计算笔记本或Web浏览器中在本地运行,而无需额外计算资源,降低屏障以创建更负责的ML模型。Gam更换器可在https://interpret.ml/gam-changer中获得。
translated by 谷歌翻译
多模式分类是人类以人为本的机器学习中的核心任务。我们观察到信息跨多模式融合在多模式融合之前,信息在偶像中具有高度互补的信息,因此在多模式融合之前可以彻底稀释。为此,我们呈现稀疏的融合变压器(SFT),一种用于现有最先进的方法的变压器的新型多模式融合方法,同时具有大大降低了内存占用和计算成本。我们想法的关键是稀疏池块,可在跨模式建模之前减少单峰令牌集合。评估在多个多模式基准数据集上进行,用于广泛的分类任务。在类似的实验条件下的多个基准上获得最先进的性能,同时报告计算成本和内存要求降低六倍。广泛的消融研究展示了在天真的方法中结合稀疏和多式化学习的好处。这铺平了在低资源设备上实现多模级学习的方式。
translated by 谷歌翻译
用于预测蛋白质之间的界面触点的计算方法对于药物发现,因此可以显着地推进替代方法的准确性,例如蛋白质 - 蛋白质对接,蛋白质功能分析工具和其他用于蛋白质生物信息学的计算方法。在这项工作中,我们介绍了几何变压器,一种用于旋转的新型几何不变性的曲线图变压器,用于旋转和平移 - 不变的蛋白质接口接触预测,包装在膨胀的端到端预测管道内。 Deepinteract预测伴侣特异性蛋白质界面触点(即,蛋白质残留物 - 残留物接触)给出了两种蛋白质的3D三级结构作为输入。在严格的基准测试中,深入的蛋白质复杂目标来自第13和第14次CASP-CAPRI实验以及对接基准5,实现14%和1.1%顶部L / 5精度(L:蛋白质单位的长度) , 分别。在这样做的情况下,使用几何变压器作为其基于图形的骨干,除了与深度兼容的其他图形的神经网络骨架之外,还优于接口接触预测的现有方法,从而验证了几何变压器学习丰富关系的有效性用于3D蛋白质结构下游任务的-Geometric特征。
translated by 谷歌翻译
We derive a set of causal deep neural networks whose architectures are a consequence of tensor (multilinear) factor analysis. Forward causal questions are addressed with a neural network architecture composed of causal capsules and a tensor transformer. The former estimate a set of latent variables that represent the causal factors, and the latter governs their interaction. Causal capsules and tensor transformers may be implemented using shallow autoencoders, but for a scalable architecture we employ block algebra and derive a deep neural network composed of a hierarchy of autoencoders. An interleaved kernel hierarchy preprocesses the data resulting in a hierarchy of kernel tensor factor models. Inverse causal questions are addressed with a neural network that implements multilinear projection and estimates the causes of effects. As an alternative to aggressive bottleneck dimension reduction or regularized regression that may camouflage an inherently underdetermined inverse problem, we prescribe modeling different aspects of the mechanism of data formation with piecewise tensor models whose multilinear projections are well-defined and produce multiple candidate solutions. Our forward and inverse neural network architectures are suitable for asynchronous parallel computation.
translated by 谷歌翻译