-
1.发明申请INVARIANT OBJECT REPRESENTATION OF IMAGES USING SPIKING NEURAL NETWORKS 审中-公开使用SPIKING神经网络的图像的不确定对象表示公开(公告)号：US20150278641A1
公开(公告)日：2015-10-01
申请号：US14228065
申请日：2014-03-27
Applicant: QUALCOMM Incorporated
Inventor： Pulkit AGRAWAL , Somdeb MAJUMDAR
CPC classification number: G06K9/4623 , G06K9/4647 , G06K9/6273 , G06N3/049 , G06N3/10
Abstract: A method for invariantly representing an object using a spiking neural network includes representing the object by a spike sequence. The method also includes determining a reference feature of the object representation. The method further includes transforming the object representation to a canonical form based on the reference feature.
Abstract translation: 使用尖峰神经网络不变地表示对象的方法包括通过尖峰序列表示对象。 该方法还包括确定对象表示的参考特征。 该方法还包括基于参考特征将对象表示转换为规范形式。
-
公开(公告)号：US20150256741A1
公开(公告)日：2015-09-10
申请号：US14520710
申请日：2014-10-22
Applicant: QUALCOMM Incorporated
Inventor： Regan Blythe TOWAL , Somdeb MAJUMDAR
CPC classification number: H04N5/23222 , G06K9/00597 , G06K9/00604 , H04N5/23219
Abstract: A method of blink and averted gaze avoidance with a camera includes detecting an averted gaze of a subject and/or one or more closed eyes of the subject in response to receiving an input to actuate a camera shutter. The method also includes scheduling actuation of the camera shutter to a future estimated time period to capture an image of the subject when a gaze direction of the subject is centered on the camera and/or both eyes of the subject are open.
Abstract translation: 使用照相机的眨眼和避免凝视回避的方法包括响应于接收到用于致动照相机快门的输入来检测被摄体和/或被摄体的一个或多个闭合眼睛的避开的视线。 该方法还包括当照相机和/或被摄体的双眼打开时，被摄体的视线方向为中心，将照相机快门调度到将来的估计时间段以捕获被摄体的图像。
-
3.发明申请FIXED POINT NEURAL NETWORK BASED ON FLOATING POINT NEURAL NETWORK QUANTIZATION 审中-公开基于浮动点神经网络定量的固定点神经网络
公开(公告)号：US20160328646A1
公开(公告)日：2016-11-10
申请号：US14920099
申请日：2015-10-22
Applicant: QUALCOMM Incorporated
Inventor： Dexu LIN , Venkata Sreekanta Reddy ANNAPUREDDY , David Edward HOWARD , David Jonathan JULIAN , Somdeb MAJUMDAR , William Richard BELL, II
CPC classification number: G06N3/08 , G06K9/4628 , G06N3/04 , G06N3/06 , G06N3/10
Abstract: A method of quantizing a floating point machine learning network to obtain a fixed point machine learning network using a quantizer may include selecting at least one moment of an input distribution of the floating point machine learning network. The method may also include determining quantizer parameters for quantizing values of the floating point machine learning network based at least in part on the at least one selected moment of the input distribution of the floating point machine learning network to obtain corresponding values of the fixed point machine learning network.
Abstract translation: 使用量化器来量化浮点计算机学习网络以获得定点机器学习网络的方法可以包括选择浮点计算机学习网络的输入分布的至少一个时刻。 该方法还可以包括：至少部分地基于浮点机器学习网络的输入分布的至少一个选定时刻来确定用于量化浮点计算机学习网络的值的量化器参数，以获得固定点计算机的相应值 学习网络
-
公开(公告)号：US20160055409A1
公开(公告)日：2016-02-25
申请号：US14528890
申请日：2014-10-30
Applicant: QUALCOMM Incorporated
Inventor： Somdeb MAJUMDAR , Regan Blythe TOWAL , Sachin Subhash TALATHI , David Jonathan JULIAN , Venkata Sreekanta Reddy ANNAPUREDDY
CPC classification number: G06N3/08 , G06N3/04 , G06N3/0427 , G06N3/049 , G06N7/005
Abstract: A method for classifying an object includes applying multiple confidence values to multiple objects. The method also includes determining a metric based on the multiple confidence values. The method further includes determining a classification of a first object from the multiple objects based on a knowledge-graph when the metric is above a threshold.
Abstract translation: 用于分类对象的方法包括将多个置信度值应用于多个对象。 该方法还包括基于多个置信度值来确定度量。 该方法还包括当度量高于阈值时，基于知识图来确定来自多个对象的第一对象的分类。
-
5.发明申请DETECTION OF UNKNOWN CLASSES AND INITIALIZATION OF CLASSIFIERS FOR UNKNOWN CLASSES 审中-公开检测未知类别和未知类别分类器的初始化
公开(公告)号：US20170039469A1
公开(公告)日：2017-02-09
申请号：US14849518
申请日：2015-09-09
Applicant: QUALCOMM Incorporated
Inventor： Somdeb MAJUMDAR , Dexu LIN , Regan Blythe TOWAL , Anthony SARAH
CPC classification number: G06N3/08 , G06K9/4628 , G06K9/6256 , G06K9/6269 , G06N3/0445 , G06N3/0454 , G06N20/00
Abstract: A method of detecting unknown classes is presented and includes generating a first classifier for multiple first classes. In one configuration, an output of the first classifier has a dimension of at least two. The method also includes designing a second classifier to receive the output of the first classifier to decide whether input data belongs to the multiple first classes or at least one second class.
Abstract translation: 提出了一种检测未知类的方法，包括生成多个第一类的第一分类器。 在一个配置中，第一分类器的输出具有至少两个维度。 该方法还包括设计第二分类器以接收第一分类器的输出以确定输入数据是属于多个第一类还是至少一个第二类。
-
公开(公告)号：US20150120628A1
公开(公告)日：2015-04-30
申请号：US14066570
申请日：2013-10-29
Applicant: QUALCOMM Incorporated
Inventor： Robert William MARSHALL , Somdeb MAJUMDAR
IPC: G06N3/08
CPC classification number: G06N3/049
Abstract: A method of frequency discrimination associated with the Doppler effect is presented. The method includes mapping a first signal to a first plurality of frequency bins and a second signal to a second plurality of frequency bins. The first signal and the second signal corresponding to different times. The method also includes firing a first plurality of neurons based on contents of the first plurality of frequency bins and firing a second plurality of neurons based on contents of the second plurality of frequency bins.
Abstract translation: 提出了一种与多普勒效应相关的频率鉴别方法。 该方法包括将第一信号映射到第一多个频率仓和第二信号到第二多个频率仓。 第一个信号和第二个信号对应不同的时间。 该方法还包括基于第一多个频率仓的内容来发射第一多个神经元，并且基于第二多个频率仓的内容点燃第二多个神经元。
-
公开(公告)号：US20180260695A1
公开(公告)日：2018-09-13
申请号：US15452449
申请日：2017-03-07
Applicant: QUALCOMM Incorporated
Inventor： Somdeb MAJUMDAR , Raghuraman KRISHNAMOORTHI
IPC: G06N3/08
CPC classification number: G06N3/08 , G06N3/0454 , G06N3/082 , G06N3/084
Abstract: A method, a computer-readable medium, and an apparatus for compressing a neural network with an unlabeled data set are provided. The apparatus may generate a first set of consecutive layers for the neural network. The first set of consecutive layers may share inputs with a second set of consecutive layers of the neural network. The apparatus may adjust weights associated with the first set of consecutive layers based on a function the difference between a first set of output values from the first set of consecutive layers and a second set of output values from the second set of consecutive layers in response to the unlabeled data set. The apparatus may remove the second set of consecutive layers from the neural network when the function of the difference between the first set of output values and the second set of output values satisfies a threshold.
-
公开(公告)号：US20180060278A1
公开(公告)日：2018-03-01
申请号：US15255015
申请日：2016-09-01
Applicant: QUALCOMM Incorporated
Inventor： Dexu LIN , Edward LIAO , Somdeb MAJUMDAR , Aaron LAMB , Karamvir CHATHA
IPC: G06F17/17
CPC classification number: G06F17/17 , G06F7/544 , G06F2207/5354
Abstract: Computing a non-linear function ƒ(x) in hardware or embedded systems can be complex and resource intensive. In one or more aspects of the disclosure, a method, a computer-readable medium, and an apparatus are provided for computing a non-linear function ƒ(x) accurately and efficiently in hardware using look-up tables (LUTs) and interpolation or extrapolation. The apparatus may be a processor. The processor computes a non-linear function ƒ(x) for an input variable x, where ƒ(x)=g(y(x),z(x)). The processor determines an integer n by determining a position of a most significant bit (MSB) of an input variable x. In addition, the processor determines a value for y(x) based on a first look-up table and the determined integer n. Also, the processor determines a value for z(x) based on n and the input variable x, and based on a second look-up table. Further, the processor computes ƒ(x) based on the determined values for y(x) and z(x).
-
公开(公告)号：US20180045818A1
公开(公告)日：2018-02-15
申请号：US15236748
申请日：2016-08-15
Applicant: QUALCOMM Incorporated
Inventor： Somdeb MAJUMDAR , Ernest OZAKI , Richard Anthony CALLE
CPC classification number: G01S13/04 , G01S7/4817 , G01S13/426 , G01S13/89 , G01S13/931 , G01S17/026 , G01S17/42 , G01S17/89 , G01S17/936
Abstract: A scanning device generally produces an image having a uniform resolution throughout a target region. To improve radar scanning/lidar scanning, an efficient scan approach to enable a radar device/lidar device to adoptively perform a scan of a target region based on interested regions and/or an adjustable resolution. The apparatus may be a scanning device for scanning. The apparatus performs a first scan over a target region to obtain a plurality of first scan samples at a plurality of locations within the target region. The apparatus generates a saliency map of the target region based on signal intensities of the plurality of first scan samples. The apparatus determines a salient region within the target region based on the saliency map. The apparatus performs at least one second scan over the salient region to obtain at least one second scan sample in the salient region.
-
公开(公告)号：US20170085774A1
公开(公告)日：2017-03-23
申请号：US14857630
申请日：2015-09-17
Applicant: QUALCOMM Incorporated
Inventor： Somdeb MAJUMDAR , Regan Blythe TOWAL , M. Anthony LEWIS
CPC classification number: H04N5/23206 , G06K9/4628 , G06K9/6227 , G06K9/6273 , G06K9/6284 , G06N3/0454 , H04N1/00307 , H04N1/00347 , H04N1/00973 , H04N1/32117 , H04N5/23216 , H04N5/23222 , H04N5/247 , H04N2201/0074
Abstract: An intelligent camera network cooperatively acquires images over a wireless network. The network automatically captures images based on a trigger. The trigger may include messages from other image capturing devices. A first image capture devices is triggered to acquire an image based on a message from at least one other image capture device.
