人类决策受到许多系统错误的困扰。可以通过提供决策辅助工具来指导决策者参与重要信息并根据理性决策策略将其集成,从而避免使用这些错误。设计这样的决策辅助工具曾经是一个乏味的手动过程。认知科学的进步可能会使将来自动化这一过程。我们最近引入了机器学习方法,以自动发现人类决策的最佳策略,并自动向人们解释这些策略。通过这种方法构建的决策辅助工具能够改善人类决策。但是,遵循该方法产生的描述非常乏味。我们假设可以通过将自动发现的决策策略作为一系列自然语言指示来克服这个问题。实验1表明,人们确实确实比以前的方法更容易理解此类程序说明。在这一发现的鼓励下,我们开发了一种将我们先前方法的输出转化为程序指示的算法。我们应用了改进的方法来自动为自然主义计划任务(即计划旅行)和自然主义决策任务(即选择抵押)生成决策辅助工具。实验2表明,这些自动产生的决策AID可显着改善人们在计划公路旅行和选择抵押贷款方面的表现。这些发现表明,AI驱动的增强可能有可能改善现实世界中的人类决策。
translated by 谷歌翻译
人们对如何分配其有限的计算资源的决定对人类智慧至关重要。这种元认知能力的一个重要组成部分决定是否继续考虑该做什么并继续下去决定。在这里,我们展示人们通过学习和反向工程师来获得这种能力的潜在的学习机制。使用外在人类规划的过程跟踪范式,我们发现人们迅速适应他们对规划成本和利益的规划。为了发现潜在的元认知学习机制,我们增强了一组具有元认知功能的加强学习模型,并执行了贝叶斯模型选择。我们的结果表明,调整规划量的元认知能力可能通过策略梯度机制来学习,该决策机制是通过传达规划价值的元认知伪奖励引导的。
translated by 谷歌翻译
We address the challenge of building domain-specific knowledge models for industrial use cases, where labelled data and taxonomic information is initially scarce. Our focus is on inductive link prediction models as a basis for practical tools that support knowledge engineers with exploring text collections and discovering and linking new (so-called open-world) entities to the knowledge graph. We argue that - though neural approaches to text mining have yielded impressive results in the past years - current benchmarks do not reflect the typical challenges encountered in the industrial wild properly. Therefore, our first contribution is an open benchmark coined IRT2 (inductive reasoning with text) that (1) covers knowledge graphs of varying sizes (including very small ones), (2) comes with incidental, low-quality text mentions, and (3) includes not only triple completion but also ranking, which is relevant for supporting experts with discovery tasks. We investigate two neural models for inductive link prediction, one based on end-to-end learning and one that learns from the knowledge graph and text data in separate steps. These models compete with a strong bag-of-words baseline. The results show a significant advance in performance for the neural approaches as soon as the available graph data decreases for linking. For ranking, the results are promising, and the neural approaches outperform the sparse retriever by a wide margin.
translated by 谷歌翻译
Few-shot learning (FSL) is a central problem in meta-learning, where learners must efficiently learn from few labeled examples. Within FSL, feature pre-training has recently become an increasingly popular strategy to significantly improve generalization performance. However, the contribution of pre-training is often overlooked and understudied, with limited theoretical understanding of its impact on meta-learning performance. Further, pre-training requires a consistent set of global labels shared across training tasks, which may be unavailable in practice. In this work, we address the above issues by first showing the connection between pre-training and meta-learning. We discuss why pre-training yields more robust meta-representation and connect the theoretical analysis to existing works and empirical results. Secondly, we introduce Meta Label Learning (MeLa), a novel meta-learning algorithm that learns task relations by inferring global labels across tasks. This allows us to exploit pre-training for FSL even when global labels are unavailable or ill-defined. Lastly, we introduce an augmented pre-training procedure that further improves the learned meta-representation. Empirically, MeLa outperforms existing methods across a diverse range of benchmarks, in particular under a more challenging setting where the number of training tasks is limited and labels are task-specific. We also provide extensive ablation study to highlight its key properties.
translated by 谷歌翻译
Large machine learning models with improved predictions have become widely available in the chemical sciences. Unfortunately, these models do not protect the privacy necessary within commercial settings, prohibiting the use of potentially extremely valuable data by others. Encrypting the prediction process can solve this problem by double-blind model evaluation and prohibits the extraction of training or query data. However, contemporary ML models based on fully homomorphic encryption or federated learning are either too expensive for practical use or have to trade higher speed for weaker security. We have implemented secure and computationally feasible encrypted machine learning models using oblivious transfer enabling and secure predictions of molecular quantum properties across chemical compound space. However, we find that encrypted predictions using kernel ridge regression models are a million times more expensive than without encryption. This demonstrates a dire need for a compact machine learning model architecture, including molecular representation and kernel matrix size, that minimizes model evaluation costs.
translated by 谷歌翻译
为了成为人类的有效伴侣,机器人必须越来越舒适地与环境接触。不幸的是,机器人很难区分``足够的''和``太多''力:完成任务需要一些力量,但太多可能会损害设备或伤害人类。设计合规的反馈控制器(例如刚度控制)的传统方法需要对控制参数进行手工调整,并使建立安全,有效的机器人合作者变得困难。在本文中,我们提出了一种新颖而易于实现的力反馈控制器,该反馈控制器使用控制屏障功能(CBF)直接从用户的最大允许力和扭矩的用户规格中得出合并的控制器。我们比较了传统僵硬控制的方法,以证明控制架构的潜在优势,并在人类机器人协作任务中证明了控制器的有效性:对笨重对象的合作操纵。
translated by 谷歌翻译
为了促进开发新模型以弥合机器和人类社会情报之间的差距,最近提议的婴儿直觉基准(Arxiv:2102.11938)提供了一系列任务,旨在评估代理商的目标和行动,即使是年轻的婴儿也表现出的表现,。在这里,我们根据层次的贝叶斯心理理论(HBTOM)提出了该基准的原则性贝叶斯解决方案。通过在代理目标和处置上包括层次的先验,对我们的HBTOM模型的推断几乎可以学习代理的效率和偏好,然后可以将其用于常识性的合理性判断,以判断有关后续代理行为。这种方法在大多数基准任务上实现了几乎完美的准确性,在产生可解释的人类的推论的同时,超过了深度学习和模仿学习基准,证明了结构化贝叶斯人的人类社会认知模型的优势。
translated by 谷歌翻译
我们研究了线性上下文的匪徒问题,其中代理必须从池中选择一个候选者,每个候选者属于敏感组。在这种情况下,候选人的奖励可能无法直接可比,例如,当代理人是雇主雇用来自不同种族的候选人时,由于歧视性偏见和/或社会不公正,有些群体的奖励较低。我们提出了一个公平的概念,该概念指出,当代理人选择一个相对排名最高的候选人时,它是公平的,这可以衡量与同一组的候选人相比,奖励的良好程度。这是一个非常强烈的公平概念,因为代理没有直接观察到相对等级,而取决于基本的奖励模型和奖励的分布。因此,我们研究了学习政策的问题,该策略在背景之间是独立的,而每个小组之间的奖励分配是绝对连续的。特别是,我们设计了一个贪婪的策略,在每个回合中,从观察到的上下文奖励对构建了脊回归估计器,然后使用经验累积分布函数计算每个候选者的相对等级的估计值。我们证明,贪婪的策略在$ t $ rounds之后达到了日志因素,并且以高概率为止,订单$ \ sqrt {dt} $的合理伪regret,其中$ d $是上下文矢量的尺寸。 The policy also satisfies demographic parity at each round when averaged over all possible information available before the selection.我们最终通过概念模拟证明,我们的政策在实践中也可以实现次线性公平伪rebret。
translated by 谷歌翻译
我们提出了一种基于深度多实例学习的简单高效的图像分类架构,并将其应用于牙科射线照片中龋齿检测的具有挑战性的任务。从技术上讲,我们的方法有两种方式贡献:首先,尽管使用弱图像级标签培训,它尽管培训了本地补丁分类概率的热线图。其次,它可以从分段标签学习,从而指导培训。与现有方法相比,人类用户可以忠实地解释预测并与模型进行交互以决定参加哪些区域。实验是在$ \ SIM $ 38K Bitewings($ \ SIM $ 316K牙齿)的大型临床数据集上进行的,在那里我们与各种基线相比实现了竞争性能。当由外部龋齿分割模型引导时,观察到分类和定位性能的显着改善。
translated by 谷歌翻译
决策森林(森林),尤其是随机森林和梯度促进树木,与许多监督学习场景中的其他方法相比,已经证明了最先进的准确性。尤其是,森林在表格数据中占主导地位,即当特征空间非结构化时,因此信号是特征指数置换的不变性。然而,在存在于多种多样(例如图像,文本和语音)深网(网络)(特别是卷积深网(Convnets))上的结构化数据中,倾向于优于森林。我们猜想至少部分原因是网络的输入不仅仅是特征幅度,也是其索引。相反,天真的森林实施未能明确考虑特征指数。最近提出的森林方法表明,对于每个节点,森林从某些特定分布中隐式采样一个随机矩阵。这些森林像某些类别的网络一样,通过将特征空间划分为对应于线性函数的凸多物体来学习。我们以这种方法为基础,并表明人们可以以多种感知方式选择分布来纳入特征区域。我们在数据上活在三个不同的流形上的数据上证明了经验性能:圆环,图像和时间序列。此外,我们证明了其在多元模拟环境中的强度,并且在预测癫痫患者的手术结果方面也表现出了优越性,并从非运动脑区域的原始立体定向EEG数据中预测运动方向。在所有模拟和真实数据中,歧管随机森林(MORF)算法的表现优于忽略特征空间结构并挑战Convnets的性能。此外,MORF运行迅速,并保持解释性和理论上的理由。
translated by 谷歌翻译