-
Patent Agency Ranking
公开(公告)号：US09904874B2
公开(公告)日：2018-02-27
申请号：US14934016
申请日：2015-11-05
Applicant: Microsoft Technology Licensing, LLC
Inventor： Mohammed Shoaib , Jie Liu
CPC classification number: G06K9/66 , G06K9/6268 , G06N3/063
Abstract: Systems, methods, and computer media for implementing convolutional neural networks efficiently in hardware are disclosed herein. A memory is configured to store a sparse, frequency domain representation of a convolutional weighting kernel. A time-domain-to-frequency-domain converter is configured to generate a frequency domain representation of an input image. A feature extractor is configured to access the memory and, by a processor, extract features based on the sparse, frequency domain representation of the convolutional weighting kernel and the frequency domain representation of the input image. The feature extractor includes convolutional layers and fully connected layers. A classifier is configured to determine, based on extracted features, whether the input image contains an object of interest. Various types of memory can be used to store different information, allowing information-dense data to be stored in faster (e.g., faster access time) memory and sparse data to be stored in slower memory.
-
公开(公告)号：US20170372362A1
公开(公告)日：2017-12-28
申请号：US15192810
申请日：2016-06-24
Applicant: Microsoft Technology Licensing, LLC
Inventor： Marcel Gavriliu , Jie Liu , Nissanka Arachchige Bodhi Priyantha , Michel Goraczko , Di Wang , Gerald Reuben DeJean , Nagendra V. Kolluru , Murali Nallappa , Vaidyaraman Sambasivam , Manish Agrawal , Srinivasa Reddy Neerudu , Dimitrios Lymberopoulos , Mohammed Shoaib
IPC: G06Q30/02
CPC classification number: G06Q30/0259 , G06Q30/0251 , G06Q30/0261 , G06Q30/0269 , G06Q30/0275
Abstract: Providing discounts to users in a physical store location. The method includes detecting that a user has stopped at a given location in the physical store. The method further includes, based on the location, identifying a set of products. The method further includes, providing an identification of the set of products to an ad server. At the ad server an auction is initiated between different product promoters to identify ads to be provided to the user. The method further includes, receiving from the ad server one or more ads to be provided to the user based on the results of the ad auction. The method further includes, providing the one or more ads to the user.
-
公开(公告)号：US10055672B2
公开(公告)日：2018-08-21
申请号：US14715554
申请日：2015-05-18
Applicant: MICROSOFT TECHNOLOGY LICENSING, LLC
Inventor： Mohammed Shoaib , Swagath Venkataramani
CPC classification number: G06K9/6267 , G06K9/00973 , G06K9/4642 , G06T1/20
Abstract: Examples of the disclosure enable efficient processing of images. In some examples, one or more interest points are identified in an image. One or more features are extracted from the identified interest points using a filter module, a gradient module, a pool module, and/or a normalizer module. The extracted features are aggregated to generate one or more vectors. Based on the generated vectors, it is determined whether the extracted features satisfy a predetermined threshold. Based on the determination, the image is classified such that the image is configured to be processed based on the classification. Aspects of the disclosure facilitate conserving memory at a local device, reducing processor load or an amount of energy consumed at the local device, and/or reducing network bandwidth usage between the local device and the remote device.
-
公开(公告)号：US09916540B2
公开(公告)日：2018-03-13
申请号：US14603222
申请日：2015-01-22
Applicant: Microsoft Technology Licensing, LLC
Inventor： Mohammed Shoaib , Jie Liu , Swagath Venkataramani
IPC: G06N99/00
CPC classification number: G06N99/005
Abstract: Scalable-effort machine learning may automatically and dynamically adjust the amount of computational effort applied to input data based on the complexity of the input data. This is in contrast to fixed-effort machine learning, which uses a one-size-fits-all approach to applying a single classifier algorithm to both simple data and complex data. Scalable-effort machine learning involves, among other things, classifiers that may be arranged as a series of multiple classifier stages having increasing complexity (and accuracy). A first classifier stage may involve relatively simple machine learning models able to classify data that is relatively simple. Subsequent classifier stages have increasingly complex machine learning models and are able to classify more complex data. Scalable-effort machine learning includes algorithms that can differentiate among data based on complexity of the data.
-
公开(公告)号：US20160267358A1
公开(公告)日：2016-09-15
申请号：US14715554
申请日：2015-05-18
Applicant: MICROSOFT TECHNOLOGY LICENSING, LLC
Inventor： Mohammed Shoaib , Swagath Venkataramani
CPC classification number: G06K9/6267 , G06K9/00973 , G06K9/4642 , G06T1/20
Abstract: Examples of the disclosure enable efficient processing of images. In some examples, one or more interest points are identified in an image. One or more features are extracted from the identified interest points using a filter module, a gradient module, a pool module, and/or a normalizer module. The extracted features are aggregated to generate one or more vectors. Based on the generated vectors, it is determined whether the extracted features satisfy a predetermined threshold. Based on the determination, the image is classified such that the image is configured to be processed based on the classification. Aspects of the disclosure facilitate conserving memory at a local device, reducing processor load or an amount of energy consumed at the local device, and/or reducing network bandwidth usage between the local device and the remote device.
Abstract translation: 本公开的示例使得能够有效地处理图像。 在一些示例中，在图像中识别一个或多个兴趣点。 使用过滤器模块，梯度模块，池模块和/或归一化模块从所识别的兴趣点提取一个或多个特征。 提取的特征被聚合以生成一个或多个向量。 基于生成的矢量，确定所提取的特征是否满足预定阈值。 基于该确定，对图像进行分类，使得图像被配置为基于分类进行处理。 本公开的方面有助于节省本地设备的存储器，减少本地设备处理器负载或消耗的能量的量，和/或减少本地设备与远程设备之间的网络带宽使用。
-
-
-
-
Search Results
15
records
(took 0.024 seconds)
