专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明授权

US10417575B2 Resource allocation for machine learning 有权
公开(公告)号：US10417575B2
公开(公告)日：2019-09-17
申请号：US13714610
申请日：2012-12-14
申请人： Microsoft Technology Licensing, LLC
发明人： Reinhard Sebastian Bernhard Nowozin , Po-Ling Loh
IPC分类号： G06N20/00
摘要： Resource allocation for machine learning is described such as for selecting between many possible options, for example, as part of an efficient training process for random decision tree training, for selecting which of many families of models best describes data, for selecting which of many features best classifies items. In various examples samples of information about uncertain options are used to score the options. In various examples, confidence intervals are calculated for the scores and used to select one or more of the options. In examples, the scores of the options may be bounded difference statistics which change little as any sample is omitted from the calculation of the score. In an example, random decision tree training is made more efficient while retaining accuracy for applications not limited to human body pose detection from depth images.

2. 发明授权

US10768825B2 Disaggregated data storage and retrieval system 有权
公开(公告)号：US10768825B2
公开(公告)日：2020-09-08
申请号：US16680865
申请日：2019-11-12
申请人： Microsoft Technology Licensing, LLC
发明人： Antony Ian Taylor Rowstron , Ioan Alexandru Stefanovici , Aaron William Ogus , Douglas Wayne Phillips , Richard John Black , Austin Nicholas Donnelly , Alexander Lloyd Gaunt , Andreas Georgiou , Ariel Gomez Diaz , Serguei Anatolievitch Legtchenko , Reinhard Sebastian Bernhard Nowozin , Benn Charles Thomsen , Hugh David Paul Williams , David Lara Saucedo , Patrick Neil Anderson , Andromachi Chatzieleftheriou , John Christopher Dainty , James Hilton Clegg , Raluca Andreea Diaconu , Rokas Drevinskas , Mengyang Yang
IPC分类号： G11B27/36 , G06F3/06 , G06N20/00 , G11B7/085
摘要： A data-storage system comprises a head receiver configured to variably receive up to a number M of write heads. The data-storage system also includes an installed number N of write heads arranged in the head receiver, a substrate receiver configured to receive one or more data-storage substrates, and a positioner machine configured to adjust a relative placement of each of the M write heads with respect to at least one of the one or more data-storage substrates.

3. 发明授权

US10110881B2 Model fitting from raw time-of-flight images 有权
公开(公告)号：US10110881B2
公开(公告)日：2018-10-23
申请号：US14528928
申请日：2014-10-30
申请人： Microsoft Technology Licensing, LLC
发明人： Jamie Daniel Joseph Shotton , Toby Sharp , Jonathan James Taylor , Pushmeet Kohli , Shahram Izadi , Andrew William Fitzgibbon , Reinhard Sebastian Bernhard Nowozin
IPC分类号： H04N13/02 , H04N13/279 , G06K9/62 , G06K9/00
摘要： Model fitting from raw time of flight image data is described, for example, to track position and orientation of a human hand or other entity. In various examples, raw image data depicting the entity is received from a time of flight camera. A 3D model of the entity is accessed and used to render, from the 3D model, simulations of raw time of flight image data depicting the entity in a specified pose/shape. The simulated raw image data and at least part of the received raw image data are compared and on the basis of the comparison, parameters of the entity are computed.

4. 发明授权

US09489639B2 Memory facilitation using directed acyclic graphs 有权
标题翻译：使用有向非循环图的内存便利
公开(公告)号：US09489639B2
公开(公告)日：2016-11-08
申请号：US14079394
申请日：2013-11-13
申请人： Microsoft Technology Licensing, LLC
发明人： Jamie Daniel Joseph Shotton , Toby Sharp , Pushmeet Kohli , Reinhard Sebastian Bernhard Nowozin , John Michael Winn , Antonio Criminisi
IPC分类号： G06N5/00 , G06N99/00 , G06K9/00 , G06K9/62
CPC分类号： G06N99/005 , G06F17/30598 , G06F17/30958 , G06K9/00335 , G06K9/00369 , G06K9/6257 , G06K9/6269 , G06K9/6282 , G06N5/003 , G06N7/005
摘要： Memory facilitation using directed acyclic graphs is described, for example, where a plurality of directed acyclic graphs are trained for gesture recognition from human skeletal data, or to estimate human body joint positions from depth images for gesture detection. In various examples directed acyclic graphs are grown during training using a training objective which takes into account both connection patterns between nodes and split function parameter values. For example, a layer of child nodes is grown and connected to a parent layer of nodes using an initialization strategy. In examples, various local search processes are used to find good combinations of connection patterns and split function parameters.
摘要翻译：描述使用有向非循环图的存储器便利化，例如，其中针对来自人类骨骼数据的手势识别训练多个有向非循环图，或者从用于手势检测的深度图像估计人体关节位置。在各种示例中，使用训练目标在训练期间生长定向非循环图，其考虑了节点之间的连接模式和分离功能参数值。例如，使用初始化策略生长子层节点并连接到父层节点。在示例中，使用各种本地搜索过程来找到连接模式和分割功能参数的良好组合。

5. 发明申请

US20210224355A1 MACHINE-LEARNING OPTIMIZATION OF DATA READING AND WRITING 有权
公开(公告)号：US20210224355A1
公开(公告)日：2021-07-22
申请号：US17301473
申请日：2021-04-05
申请人： Microsoft Technology Licensing, LLC
发明人： Ioan Alexandru STEFANOVICI , Benn Charles Thomsen , Alexander Lloyd Gaunt , Antony Ian Taylor Rowstron , Reinhard Sebastian Bernhard Nowozin
IPC分类号： G06F17/18 , G06F11/36 , G06N20/00 , G06F16/2458 , G11B20/10 , H03M13/37 , H03M5/06
摘要： Examples are disclosed that relate to encoding data on a data-storage medium. The method comprises obtaining a representation of a measurement performed on the data-storage medium, the representation being based on a previously recorded pattern of data encoded in the data-storage medium in a layout that defines a plurality of data locations. The method further comprises inputting the representation into a data decoder comprising a trained machine-learning function, and obtaining from the data decoder, for each data location of the layout, a plurality of probability values, wherein each probability value is associated with a corresponding data value and represents the probability that the corresponding data value matches the actual data value in the previously recorded pattern of data at a same location in the layout.

6. 发明授权

US09373087B2 Decision tree training in machine learning 有权
标题翻译：机器学习中的决策树训练
公开(公告)号：US09373087B2
公开(公告)日：2016-06-21
申请号：US13660692
申请日：2012-10-25
申请人： MICROSOFT TECHNOLOGY LICENSING, LLC
发明人： Reinhard Sebastian Bernhard Nowozin
IPC分类号： G06F15/18 , G06N99/00
CPC分类号： G06N99/005
摘要： Improved decision tree training in machine learning is described, for example, for automated classification of body organs in medical images or for detection of body joint positions in depth images. In various embodiments, improved estimates of uncertainty are used when training random decision forests for machine learning tasks in order to give improved accuracy of predictions and fewer errors. In examples, bias corrected estimates of entropy or Gini index are used or non-parametric estimates of differential entropy. In examples, resulting trained random decision forests are better able to perform classification or regression tasks for a variety of applications without undue increase in computational load.
摘要翻译：描述了机器学习中的改进的决策树训练，例如用于医学图像中的身体器官的自动分类或用于在深度图像中检测身体关节位置。在各种实施例中，当训练用于机器学习任务的随机决策树时，使用改进的不确定性估计，以提高预测的准确性和更少的错误。在实例中，使用熵或Gini指数的偏差修正估计或差分熵的非参数估计。在实例中，得到的训练有素的随机决策树能够更好地对各种应用执行分类或回归任务，而不会过度增加计算量。

7. 发明授权

US10970363B2 Machine-learning optimization of data reading and writing 有权
公开(公告)号：US10970363B2
公开(公告)日：2021-04-06
申请号：US15786347
申请日：2017-10-17
申请人： Microsoft Technology Licensing, LLC
发明人： Ioan Alexandru Stefanovici , Benn Charles Thomsen , Alexander Lloyd Gaunt , Antony Ian Taylor Rowstron , Reinhard Sebastian Bernhard Nowozin
IPC分类号： G06F17/18 , G11B20/10 , H03M13/37 , H03M5/06 , G06F16/2458 , G06N20/00 , G06F11/36
摘要： Examples are disclosed that relate to reading stored data. The method comprises obtaining a representation of a measurement performed on a data-storage medium, the representation being based on a previously recorded pattern of data encoded in the data-storage medium in a layout that defines a plurality of data locations. The method further comprises inputting the representation into a data decoder comprising a trained machine-learning function, and obtaining from the data decoder, for each data location of the layout, a plurality of probability values, wherein each probability value is associated with a corresponding data value and represents the probability that the corresponding data value matches the actual data value in the previously recorded pattern of data at a same location in the layout.

8. 发明申请

US20170147947A1 MEMORY FACILITATION USING DIRECTED ACYCLIC GRAPHS 审中-公开
公开(公告)号：US20170147947A1
公开(公告)日：2017-05-25
申请号：US15338050
申请日：2016-10-28
申请人： Microsoft Technology Licensing, LLC
发明人： Jamie Daniel Joseph Shotton , Toby Sharp , Pushmeet Kohli , Reinhard Sebastian Bernhard Nowozin , John Michael Winn , Antonio Criminisi
IPC分类号： G06N99/00 , G06K9/62 , G06K9/00 , G06F17/30 , G06N7/00
摘要： Memory facilitation using directed acyclic graphs is described, for example, where a plurality of directed acyclic graphs are trained for gesture recognition from human skeletal data, or to estimate human body joint positions from depth images for gesture detection. In various examples directed acyclic graphs are grown during training using a training objective which takes into account both connection patterns between nodes and split function parameter values. For example, a layer of child nodes is grown and connected to a parent layer of nodes using an initialization strategy. In examples, various local search processes are used to find good combinations of connection patterns and split function parameters.

9. 发明申请

US20160127715A1 MODEL FITTING FROM RAW TIME-OF-FLIGHT IMAGES 审中-公开
标题翻译：从原始时间飞行图像配置的模型
公开(公告)号：US20160127715A1
公开(公告)日：2016-05-05
申请号：US14528928
申请日：2014-10-30
申请人： Microsoft Technology Licensing, LLC
发明人： Jamie Daniel Joseph Shotton , Toby Sharp , Jonathan James Taylor , Pushmeet Kohli , Shahram Izadi , Andrew William Fitzgibbon , Reinhard Sebastian Bernhard Nowozin
IPC分类号： H04N13/02 , G06K9/00 , G06K9/62
CPC分类号： H04N13/279 , G06K9/00214 , G06K9/00382 , G06K9/00389 , G06K9/6202
摘要： Model fitting from raw time of flight image data is described, for example, to track position and orientation of a human hand or other entity. In various examples, raw image data depicting the entity is received from a time of flight camera. A 3D model of the entity is accessed and used to render, from the 3D model, simulations of raw time of flight image data depicting the entity in a specified pose/shape. The simulated raw image data and at least part of the received raw image data are compared and on the basis of the comparison, parameters of the entity are computed.
摘要翻译：描述从原始飞行时间图像数据的模型拟合，例如，跟踪人手或其他实体的位置和方位。在各种示例中，从飞行时间相机接收描绘实体的原始图像数据。实体的3D模型被访问并用于从3D模型渲染描绘以特定姿态/形状的实体的飞行时间图像数据的模拟。对模拟的原始图像数据和至少部分接收到的原始图像数据进行比较，并且基于比较，计算实体的参数。

10. 发明授权

US10832163B2 Memory facilitation using directed acyclic graphs 有权
公开(公告)号：US10832163B2
公开(公告)日：2020-11-10
申请号：US15338050
申请日：2016-10-28
申请人： Microsoft Technology Licensing, LLC
发明人： Jamie Daniel Joseph Shotton , Toby Sharp , Pushmeet Kohli , Reinhard Sebastian Bernhard Nowozin , John Michael Winn , Antonio Criminisi
IPC分类号： G06N20/00 , G06N5/00 , G06F16/28 , G06F16/901 , G06K9/00 , G06K9/62 , G06N7/00
摘要： Memory facilitation using directed acyclic graphs is described, for example, where a plurality of directed acyclic graphs are trained for gesture recognition from human skeletal data, or to estimate human body joint positions from depth images for gesture detection. In various examples directed acyclic graphs are grown during training using a training objective which takes into account both connection patterns between nodes and split function parameter values. For example, a layer of child nodes is grown and connected to a parent layer of nodes using an initialization strategy. In examples, various local search processes are used to find good combinations of connection patterns and split function parameters.

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式