Learning universal representations across different applications domain is an open research problem. In fact, finding universal architecture within the same application but across different types of datasets is still unsolved problem too, especially in applications involving processing 3D point clouds. In this work we experimentally test several state-of-the-art learning-based methods for 3D point cloud registration against the proposed non-learning baseline registration method. The proposed method either outperforms or achieves comparable results w.r.t. learning based methods. In addition, we propose a dataset on which learning based methods have a hard time to generalize. Our proposed method and dataset, along with the provided experiments, can be used in further research in studying effective solutions for universal representations. Our source code is available at: github.com/DavidBoja/greedy-grid-search.
translated by 谷歌翻译
Probabilistic context-free grammars have a long-term record of use as generative models in machine learning and symbolic regression. When used for symbolic regression, they generate algebraic expressions. We define the latter as equivalence classes of strings derived by grammar and address the problem of calculating the probability of deriving a given expression with a given grammar. We show that the problem is undecidable in general. We then present specific grammars for generating linear, polynomial, and rational expressions, where algorithms for calculating the probability of a given expression exist. For those grammars, we design algorithms for calculating the exact probability and efficient approximation with arbitrary precision.
translated by 谷歌翻译
从未标记数据学习的需要在当代机器学习中增加。无监督特征排名的方法,该方法识别这些数据中最重要的特征是越来越关注,因此它们在研究高吞吐量生物实验或用户基础时的应用程序。我们提出了Frane(通过属性网络排名),一种无监督算法,能够在给定的未标记数据集中找到关键特征。Frane基于网络重建和网络分析的思路。正如我们经验上展示了大量基准的那样,Frane比最先进的竞争对手表现更好。此外,我们提供了Frane的时间复杂性分析进一步证明其可扩展性。最后,Frane优惠由于结果可解释的关系结构用于推导特征重要性。
translated by 谷歌翻译
我们展示了自我监督学习的使用来探索和利用大型未标记的数据集。从最新数据释放的暗能谱仪器(DESI)传统成像调查中侧重于4200万个Galaxy图像,我们首先培养一个自我监督模型来蒸馏到对称,不确定性和每个噪声的强大稳健图片。然后,我们使用表示来构建和公开发布交互式语义相似性搜索工具。我们展示了我们的工具如何用于迅速发现罕见的物体,仅给出一个例子,提高人群采购活动的速度,并构建和改进监督应用程序的培训集。虽然我们专注于Sky调查的图像,但该技术很简单适用于任何维度的任何科学数据集。可以在https://github.com/georgestein/galaxy_search找到相似性搜索Web应用程序
translated by 谷歌翻译
我们采用自我监督的代表性学习来从深色能源仪器遗产成像调查的数据释放9中从7600万个星系图像中提取信息9.针对新的强力引力镜头候选者的识别,我们首先创建了快速的相似性搜索工具,以发现新的搜索工具强镜仅给出一个单个标记的示例。然后,我们展示如何在自我监督的表示上训练简单的线性分类器,仅需几分钟即可在CPU上进行几分钟,可以自动以极高的效率对强镜进行分类。我们提出了1192个新的强镜候选者,我们通过简短的视觉标识活动确定,并释放一种基于Web的相似性搜索工具和顶级网络预测,以促进众包快速发现额外的强力镜头和其他稀有物体:HTTPS:https://github.com/georgestein/ssl-legacysurvey。
translated by 谷歌翻译
基于强化学习(RL)的最先进的决策系统是数据驱动的黑盒神经模型,在那里通常难以将专家知识纳入模型或让专家审查和验证学习决策机制。知识插入和模型审查是许多涉及人类健康和安全的应用中的重要要求。一种桥接数据和知识驱动系统之间差距的方法是程序合成:替换用神经网络生成的符号节目或通过遗传编程输出决策的神经网络。我们提出了一种新的编程语言,BF ++,专为在部分观察到的马尔可夫决策过程(POMDP)设置中的代理程序自动编程,并应用神经节目综合来解决标准Openai健身房基准。
translated by 谷歌翻译