专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

41. 发明授权

US5412670A N-bit parity neural network encoder 失效
标题翻译： N位奇偶校验神经网络编码器
公开(公告)号：US5412670A
公开(公告)日：1995-05-02
申请号：US983659
申请日：1992-11-30
申请人： David G. Stork , James D. Allen
发明人： David G. Stork , James D. Allen
IPC分类号： G06F15/18 , G06F11/10 , G06N3/04 , G06N99/00 , H03M7/00 , H03M13/09
CPC分类号： G06F11/1032 , G06N3/04 , H03M13/09
摘要： A three layer artificial neural network having an N terminal input, a two cell hidden and a single cell output layer generates an output parity signal indicating whether an even or an odd number of binary bits are asserted at the N terminal input. The two hidden layer neural cells have activation functions that cause deviations about a linear response characteristic that allow the classification of a signal representative of the number of asserted input bits into odd and even groups. This network represents a significant reduction in the number of hidden units previously required because of the particular form of activation transfer characteristic used in the two hidden layer neural cells.
摘要翻译：具有N端子输入，两个单元隐藏和单个单元输出层的三层人造神经网络产生指示在N端子输入处是偶数还是奇数二进制位被断言的输出奇偶校验信号。两个隐层神经细胞具有激活功能，其引起关于线性响应特性的偏差，该线性响应特性允许将表示被确定的输入比特数的信号分类为奇数和偶数组。由于两个隐层神经细胞中使用的特定形式的激活转移特性，这个网络代表了先前需要的隐藏单元数量的显着减少。

42. 发明授权

US5157275A Circuit employing logical gates for calculating activation function derivatives on stochastically-encoded signals 失效
标题翻译：电路采用逻辑门来计算随机编码信号上的激活函数导数
公开(公告)号：US5157275A
公开(公告)日：1992-10-20
申请号：US673804
申请日：1991-03-22
申请人： David G. Stork , Ronald C. Keesing
发明人： David G. Stork , Ronald C. Keesing
IPC分类号： G06F15/18 , G06G7/60 , G06N3/06 , G06N3/063 , G06N99/00
CPC分类号： G06N3/0635
摘要： A circuit employing logical gates for calculating activation function derivatives on stochastically encoded signals. In one embodiment a two input nonlinear circuit calculates neuron activation functions suitable for gradient-descent learning.
摘要翻译：采用逻辑门的电路用于计算随机编码的信号上的激活函数导数。在一个实施例中，两输入非线性电路计算适合于梯度下降学习的神经元激活函数。

43. 发明授权

US09471728B2 Metrics for designing a plenoptic imaging system 有权
标题翻译：设计全景成像系统的指标
公开(公告)号：US09471728B2
公开(公告)日：2016-10-18
申请号：US14022074
申请日：2013-09-09
申请人： Sapna A. Shroff , Kathrin Berkner , David G. Stork
发明人： Sapna A. Shroff , Kathrin Berkner , David G. Stork
IPC分类号： G06F17/50 , H04N5/232 , G02B7/38
CPC分类号： G06F17/5009 , G02B7/38 , H04N5/23212
摘要： Metrics for characterizing the focusing of a plenoptic imaging system. In one aspect, the metric is based on the high frequency content and/or the blurring of the plenoptic image.
摘要翻译：表征全景成像系统聚焦的指标。在一个方面，度量是基于高频内容和/或全视觉图像的模糊。

44. 发明申请

US20150264245A1 Adaptive Image Acquisition for Multiframe Reconstruction 有权
标题翻译：多帧重建的自适应图像采集
公开(公告)号：US20150264245A1
公开(公告)日：2015-09-17
申请号：US14551998
申请日：2014-11-24
申请人： M. Dirk Robinson , Junlan Yang , David G. Stork
发明人： M. Dirk Robinson , Junlan Yang , David G. Stork
IPC分类号： H04N5/235 , G06T1/00 , H04N5/232 , G06T7/00
CPC分类号： H04N5/2355 , G06T1/0007 , G06T5/50 , G06T7/571 , G06T7/97 , G06T2207/10004 , G06T2207/20208 , H04N5/23212 , H04N5/235 , H04N5/2352 , H04N5/2356
摘要： Multiframe reconstruction combines a set of acquired images into a reconstructed image. Here, which images to acquire are selected based at least in part on the content of previously acquired images. In one approach, a set of at least three images of an object are acquired at different acquisition settings. For at least one of the images in the set, the acquisition setting for the image is determined based at least in part on the content of previously acquired images. Multiframe image reconstruction is applied to the set of acquired images to synthesize a reconstructed image of the object.
摘要翻译：多帧重建将一组获取的图像组合成重建的图像。这里，至少部分地基于先前获取的图像的内容来选择要获取的图像。在一种方法中，在不同的获取设置下获取对象的至少三个图像的集合。对于集合中的至少一个图像，至少部分地基于先前获取的图像的内容来确定图像的获取设置。将多帧图像重建应用于所获取的图像集合以合成对象的重建图像。

45. 发明授权

US08949260B2 Method and apparatus for secure and oblivious document matching 有权
标题翻译：安全和遗忘文件匹配的方法和装置
公开(公告)号：US08949260B2
公开(公告)日：2015-02-03
申请号：US12576943
申请日：2009-10-09
申请人： David G. Stork , Mohammed Shoaib
发明人： David G. Stork , Mohammed Shoaib
IPC分类号： G06F17/30 , G06F7/00 , G06K9/62 , G06K9/00 , H04L9/32
CPC分类号： G06K9/6276 , G06F17/30011 , G06K9/00442 , H04L9/3218 , H04L2209/50 , H04L2209/605
摘要： A method and apparatus for secure and oblivious document matching are described. In one embodiment, the method comprises transmitting initial secure dot product data generated from a document thumbprint for a document to a remote system. The method may also comprise receiving a response from the remote system. In one embodiment, the response is generated by the remote system utilizing the initial secure dot product data and without knowledge of the document. In one embodiment, the method may further comprise determining whether the response indicates a match for the document.
摘要翻译：描述了用于安全和遗忘的文档匹配的方法和装置。在一个实施例中，该方法包括将从文档的文档指纹生成的初始安全点产品数据传输到远程系统。该方法还可以包括从远程系统接收响应。在一个实施例中，响应由远程系统利用初始安全点产品数据生成，而不知道文档。在一个实施例中，该方法还可以包括确定响应是否指示文档的匹配。

46. 发明申请

US20140074606A1 METHOD, SYSTEM AND COMPUTER CODE FOR CONTENT BASED WEB ADVERTISING 审中-公开
标题翻译：基于内容的网络广告的方法，系统和计算机代码
公开(公告)号：US20140074606A1
公开(公告)日：2014-03-13
申请号：US14078065
申请日：2013-11-12
申请人： Jamey Graham , David G. Stork , Chuck Lam
发明人： Jamey Graham , David G. Stork , Chuck Lam
IPC分类号： G06Q30/02
CPC分类号： G06Q30/0255 , G06Q30/02 , G06Q30/0242 , G06Q30/0251 , G06Q30/0257 , G06Q30/0277
摘要： According to the present invention, an internet target marketing system, method and computer program for distributing online advertising to viewers based upon the viewers' interests is provided. Specific embodiments according to the present invention can use an n-way matching of user's concepts of interest, advertiser's concepts and a currently viewed document to target advertising to the view of the current document. Some embodiments can generate a contextually sensitive advertisement for each page viewed in a browser, thereby associating an advertisement with every page in a document. Specific embodiments can associate advertising with documents that are substantially free of embedded advertisements, for example. Alternative embodiments can include embedded advertising, however.
摘要翻译：根据本发明，提供了一种基于观众的兴趣向观众分发网络广告的互联网目标营销系统，方法和计算机程序。根据本发明的具体实施例可以使用用户感兴趣的概念，广告主的概念和当前浏览的文档的n-way匹配来将广告定位到当前文档的视图。一些实施例可以为在浏览器中查看的每个页面生成上下文敏感广告，从而将广告与文档中的每个页面相关联。具体实施例可以将广告与基本上不含嵌入式广告的文档相关联。然而，替代实施例可以包括嵌入式广告。

47. 发明申请

US20140019098A1 Metrics for Designing a Plenoptic Imaging System 有权
标题翻译：设计专业成像系统的指标
公开(公告)号：US20140019098A1
公开(公告)日：2014-01-16
申请号：US14022074
申请日：2013-09-09
申请人： Sapna A. Shroff , Kathrin Berkner , David G. Stork
发明人： Sapna A. Shroff , Kathrin Berkner , David G. Stork
IPC分类号： G06F17/50
CPC分类号： G06F17/5009 , G02B7/38 , H04N5/23212
摘要： Metrics for characterizing the focusing of a plenoptic imaging system. In one aspect, the metric is based on the high frequency content and/or the blurring of the plenoptic image.
摘要翻译：表征全景成像系统聚焦的指标。在一个方面，度量是基于高频内容和/或全视觉图像的模糊。

48. 发明申请

US20120201378A1 EFFICIENT, REMOTE, PRIVATE TREE-BASED CLASSIFICATION USING CRYPTOGRAPHIC TECHNIQUES 有权
标题翻译：高效，远程，基于树的基于分类技术的分类
公开(公告)号：US20120201378A1
公开(公告)日：2012-08-09
申请号：US13020708
申请日：2011-02-03
申请人： Mohamed Nabeel , David G. Stork
发明人： Mohamed Nabeel , David G. Stork
IPC分类号： H04L9/00
CPC分类号： H04L9/008 , H04L2209/50
摘要： A method and apparatus are disclosed herein for classification. In one embodiment, the method comprises performing tree-based classification of a user input by a classifier with a classification tree at a first location, including exchanging data with a second location, different from the first location, to obtain the user input and provide results of classification to a user using singly homomorphic encryption so that the user input is not revealed to the classifier, the classification tree is not revealed to the user and the classifier's output is not revealed to the classifier.
摘要翻译：本文公开了用于分类的方法和装置。在一个实施例中，该方法包括在第一位置处由分类器对分类器进行用户输入的基于树的分类，包括与第一位置不同的第二位置交换数据，以获得用户输入并提供结果对使用单一同态加密的用户进行分类，使得用户输入不会向分类器显示，分类树不会向用户显示，分类器的输出不会显示给分类器。

49. 发明申请

US20100053411A1 Control of Adaptive Optics Based on Post-Processing Metrics 有权
标题翻译：基于后处理度量的自适应光学控制
公开(公告)号：US20100053411A1
公开(公告)日：2010-03-04
申请号：US12198765
申请日：2008-08-26
申请人： M. Dirk Robinson , David G. Stork
发明人： M. Dirk Robinson , David G. Stork
IPC分类号： G02B13/16
CPC分类号： G02B26/06
摘要： Adaptive optics (AO) elements in imaging system allow dynamic and precise control over the optical wavefront to reduce uncontrolled wavefront errors in imaging systems. Traditional control of such devices is based on inverting the wavefront function to minimize the RMS wavefront error. However, this approach is not always optimal, particularly when the wavefront error is near or exceeds the limit of the AO element's correction capability. In the current approach, the AO element is instead controlled based on a performance metric that takes into account image processing, and not just RMS wavefront error.
摘要翻译：成像系统中的自适应光学（AO）元件允许对光学波前进行动态和精确的控制，以减少成像系统中不受控制的波前误差。这种设备的传统控制是基于反转波前函数来最小化RMS波前误差。然而，这种方法并不总是最佳的，特别是当波前误差接近或超过AO元件校正能力的极限时。在当前的方法中，AO元素是根据考虑到图像处理的性能指标来控制的，而不仅仅是RMS波前误差。

50. 发明申请

US20090245688A1 Adaptive image acquisition for multiframe reconstruction 有权
标题翻译：用于多帧重建的自适应图像采集
公开(公告)号：US20090245688A1
公开(公告)日：2009-10-01
申请号：US12079555
申请日：2008-03-26
申请人： M. Dirk Robinson , Junlan Yang , David G. Stork
发明人： M. Dirk Robinson , Junlan Yang , David G. Stork
IPC分类号： G06K9/36
CPC分类号： H04N5/2355 , G06T1/0007 , G06T5/50 , G06T7/571 , G06T7/97 , G06T2207/10004 , G06T2207/20208 , H04N5/23212 , H04N5/235 , H04N5/2352 , H04N5/2356
摘要： Multiframe reconstruction combines a set of acquired images into a reconstructed image. Here, which images to acquire are selected based at least in part on the content of previously acquired images. In one approach, a set of at least three images of an object are acquired at different acquisition settings. For at least one of the images in the set, the acquisition setting for the image is determined based at least in part on the content of previously acquired images. Multiframe image reconstruction is applied to the set of acquired images to synthesize a reconstructed image of the object.
摘要翻译：多帧重建将一组获取的图像组合成重建的图像。这里，至少部分地基于先前获取的图像的内容来选择要获取的图像。在一种方法中，在不同的获取设置下获取对象的至少三个图像的集合。对于集合中的至少一个图像，至少部分地基于先前获取的图像的内容来确定图像的获取设置。将多帧图像重建应用于所获取的图像集合以合成对象的重建图像。

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