公开(公告)号：US08812274B2

公开(公告)日：2014-08-19

申请号：US12767533

申请日：2010-04-26

申请人： Hemant Virkar ,  Karen Stark ,  Jacob Borgman

发明人： Hemant Virkar ,  Karen Stark ,  Jacob Borgman

IPC分类号： G06F17/10 ,  G06N3/08

CPC分类号： G06N99/005 ,  G06K9/6232 ,  G06K9/6254

摘要： Methods and systems for creating ensembles of hypersurfaces in high-dimensional feature spaces, and to machines and systems relating thereto. More specifically, exemplary aspects of the invention relate to methods and systems for generating supervised hypersurfaces based on user domain expertise, machine learning techniques, or other supervised learning techniques. These supervised hypersurfaces may optionally be combined with unsupervised hypersurfaces derived from unsupervised learning techniques. Lower-dimensional subspaces may be determined by the methods and systems for creating ensembles of hypersurfaces in high-dimensional feature spaces. Data may then be projected onto the lower-dimensional subspaces for use, e.g., in further data discovery, visualization for display, or database access. Also provided are tools, systems, devices, and software implementing the methods, and computers embodying the methods and/or running the software, where the methods, software, and computers utilize various aspects of the present invention relating to analyzing data.

摘要翻译： 用于在高维特征空间中创建超曲面集合的方法和系统以及与之相关的机器和系统。 更具体地，本发明的示例性方面涉及用于基于用户领域专长，机器学习技术或其他监督学习技术来生成监督超曲面的方法和系统。 这些监督超表面可以可选地与从无监督的学习技术衍生的无监督的超曲面组合。 低维子空间可以通过用于在高维特征空间中创建超曲面集合的方法和系统来确定。 然后可以将数据投影到较低维度子空间上以供使用，例如在进一步的数据发现，显示可视化或数据库访问中。 还提供了实现方法的工具，系统，设备和软件以及体现方法和/或运行软件的计算机，其中方法，软件和计算机利用与分析数据相关的本发明的各个方面。

公开(公告)号：US08386401B2

公开(公告)日：2013-02-26

申请号：US12557344

申请日：2009-09-10

申请人： Hemant Virkar ,  Karen Stark ,  Jacob Borgman

发明人： Hemant Virkar ,  Karen Stark ,  Jacob Borgman

IPC分类号： G06F15/18

CPC分类号： G06N99/005 ,  G06N3/02

摘要： Methods for training machines to categorize data, and/or recognize patterns in data, and machines and systems so trained. More specifically, variations of the invention relates to methods for training machines that include providing one or more training data samples encompassing one or more data classes, identifying patterns in the one or more training data samples, providing one or more data samples representing one or more unknown classes of data, identifying patterns in the one or more of the data samples of unknown class(es), and predicting one or more classes to which the data samples of unknown class(es) belong by comparing patterns identified in said one or more data samples of unknown class with patterns identified in said one or more training data samples. Also provided are tools, systems, and devices, such as support vector machines (SVMs) and other methods and features, software implementing the methods and features, and computers or other processing devices incorporating and/or running the software, where the methods and features, software, and processors utilize specialized methods to analyze data.

摘要翻译： 用于训练机器对数据进行分类和/或识别数据中的模式以及如此训练的机器和系统的方法。 更具体地，本发明的变型涉及用于训练机器的方法，所述方法包括提供包含一个或多个数据类别的一个或多个训练数据样本，识别所述一个或多个训练数据样本中的模式，提供一个或多个表示一个或多个 未知类别的数据样本的未知类别，识别未知类别的一个或多个数据样本中的模式，以及通过比较在所述一个或多个类别中识别的模式来预测未知类别的数据样本所属于的一个或多个类别 在所述一个或多个训练数据样本中识别的模式的未知类别的数据样本。 还提供了工具，系统和设备，例如支持向量机（SVM）和其他方法和特征，实现方法和特征的软件，以及结合和/或运行软件的计算机或其他处理设备，其中方法和特征 ，软件和处理器利用专门的方法分析数据。

公开(公告)号：US20200090408A1

公开(公告)日：2020-03-19

申请号：US16570369

申请日：2019-09-13

申请人： Hemant Virkar

发明人： Hemant Virkar ,  Leah Kaplan ,  Stephen Furlani ,  Jacob Borgman

IPC分类号： G06T19/00 ,  G06T7/215 ,  G06T7/73 ,  G06N20/20 ,  G06K9/00

摘要： The disclosure relates to a system for providing guidance for positioning a body. The system may include a video display, one or more digital cameras configured to generate a depth video stream and a visual video stream, and a computing device including, a memory, and a processor. The processor may control the one or more digital cameras to generate the depth video stream including a depth image of the body and the visual video stream including a color image of the body. The processor identifies at least a part of the body within the images using a first trained learning machine to segment the images and isolate the body. The processor may crop both the visual image and the depth image based on the identified body. The processor may estimate a position of a plurality of joints of the body by applying a second trained learning machine to the identified and isolated part of the body. The processor may generate a current pose estimate by connecting estimated positions of the plurality of joints. The processor may overlay a visual representation of the current pose estimate over the color video stream on the video display.

公开(公告)号：US10546245B2

公开(公告)日：2020-01-28

申请号：US14337711

申请日：2014-07-22

申请人： Hemant Virkar

发明人： Hemant Virkar ,  Karen Stark ,  Jacob Borgman

IPC分类号： G06N99/00 ,  G06N20/00

摘要： Methods and systems for creating ensembles of hypersurfaces in high-dimensional feature spaces, and to machines and systems relating thereto. More specifically, exemplary aspects of the invention relate to methods and systems for generating supervised hypersurfaces based on user domain expertise, machine learning techniques, or other supervised learning techniques. These supervised hypersurfaces may optionally be combined with unsupervised hypersurfaces derived from unsupervised learning techniques. Lower-dimensional subspaces may be determined by the methods and systems for creating ensembles of hypersurfaces in high-dimensional feature spaces. Data may then be projected onto the lower-dimensional subspaces for use, e.g., in further data discovery, visualization for display, or database access. Also provided are tools, systems, devices, and software implementing the methods, and computers embodying the methods and/or running the software, where the methods, software, and computers utilize various aspects of the present invention relating to analyzing data.