公开(公告)号：WO2015148254A3

公开(公告)日：2016-01-07

申请号：PCT/US2015021428

申请日：2015-03-19

Applicant: QUALCOMM INC

Inventor： AGRAWAL PULKIT ,  MAJUMDAR SOMDEB ,  GUPTA VIKRAM

IPC: G06N3/04 ,  G06K9/46

CPC classification number: G06K9/4647 ,  G06K9/4619 ,  G06K9/6273 ,  G06N3/049

Abstract: A method for generating a histogram in a spiking neural network includes counting spikes associated with a latency encoded representation of an object. The method also includes generating the histogram based on the spike count.

Abstract translation: 用于在加标神经网络中生成直方图的方法包括计数与对象的等待时间编码表示相关联的峰值。 该方法还包括基于尖峰计数生成直方图。

公开(公告)号：EP3295385A1

公开(公告)日：2018-03-21

申请号：EP16718825

申请日：2016-04-14

Applicant: QUALCOMM INC

Inventor： LIN DEXU ,  ANNAPUREDDY VENKATA SREEKANTA REDDY ,  HOWARD DAVID EDWARD ,  JULIAN DAVID JONATHAN ,  MAJUMDAR SOMDEB ,  BELL II WILLIAM RICHARD

IPC: G06N3/10 ,  G06N3/06

CPC classification number: G06N3/08 ,  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.

公开(公告)号：WO2014025619A2

公开(公告)日：2014-02-13

申请号：PCT/US2013053290

申请日：2013-08-01

Applicant: QUALCOMM INC

Inventor： MAJUMDAR SOMDEB ,  RANGAN VENKAT ,  LEVIN JEFFREY A

IPC: G06N3/04

CPC classification number: G06N3/02 ,  G06N3/049 ,  G10L19/038 ,  G10L19/12

Abstract: Certain aspects of the present disclosure support a technique for optimized representation of variables in neural systems. Bit-allocation for neural signals and parameters in a neural network described in the present disclosure may comprise allocating quantization levels to the neural signals based on at least one measure of sensitivity of a pre-determined performance metric to quantization errors in the neural signals, and allocating bits to the parameters based on the at least one measure of sensitivity of the pre-determined performance metric to quantization errors in the parameters.

Abstract translation: 本公开的某些方面支持用于神经系统中变量的优化表示的技术。 在本公开中描述的神经网络中的神经信号和参数的位分配可以包括基于对神经信号中的量化误差的预定性能度量的灵敏度的至少一个度量来为神经信号分配量化级别，以及 基于对所述参数中的量化误差的所述预定性能度量的灵敏度的至少一个度量来将比特分配给所述参数。

公开(公告)号：WO2012012189A3

公开(公告)日：2012-04-05

申请号：PCT/US2011042432

申请日：2011-06-29

Applicant: QUALCOMM INC ,  GARUDADRI HARINATH ,  BAHETI PAWAN KUMAR ,  MAJUMDAR SOMDEB

Inventor： GARUDADRI HARINATH ,  BAHETI PAWAN KUMAR ,  MAJUMDAR SOMDEB

IPC: A61B5/053 ,  H03M1/12 ,  H03M7/30

CPC classification number: A61B5/0531 ,  A61B5/0022 ,  A61B5/0024 ,  A61B5/02416 ,  A61B5/0402 ,  A61B5/0536 ,  A61B5/0816 ,  A61B5/14551 ,  A61B5/7232 ,  H03M7/30

Abstract: Certain aspects of the present disclosure relate to techniques for measuring body impedance based on baseband signal detection in analog domain. Proposed methods and apparatus are able to measure an impedance of human body based on sub-Nyquist sampling of signals. The proposed techniques can be particularly beneficial for reducing overall sensor power when an actuation signal generates electrical signals corresponding to vital signs in humans.

Abstract translation: 本公开的某些方面涉及基于模拟域中的基带信号检测来测量身体阻抗的技术。 提出的方法和装置能够基于子奈奎斯特信号采样来测量人体的阻抗。 当致动信号产生对应于人类生命体征的电信号时，所提出的技术可以特别有利于降低总传感器功率。

公开(公告)号：WO2017023551A3

公开(公告)日：2017-04-13

申请号：PCT/US2016043146

申请日：2016-07-20

Applicant: QUALCOMM INC

Inventor： MAJUMDAR SOMDEB ,  LIN DEXU ,  TOWAL REGAN BLYTHE ,  SARAH ANTHONY

IPC: G06N99/00 ,  G06K9/62 ,  G06N3/04

CPC classification number: G06N3/08 ,  G06K9/4628 ,  G06K9/6256 ,  G06K9/6269 ,  G06N3/0445 ,  G06N3/0454 ,  G06N99/005

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：WO2015148369A3

公开(公告)日：2015-12-10

申请号：PCT/US2015021991

申请日：2015-03-23

Applicant: QUALCOMM INC

Inventor： AGRAWAL PULKIT ,  MAJUMDAR SOMDEB

IPC: G06N3/04 ,  G06K9/00 ,  G06N3/10

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：WO2015065850A2

公开(公告)日：2015-05-07

申请号：PCT/US2014062257

申请日：2014-10-24

Applicant: QUALCOMM INC

Inventor： MARSHALL ROBERT WILLIAM ,  MAJUMDAR SOMDEB

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: 介绍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并将第二信号映射到第二多个频率仓。 第一信号和第二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触发第一多个神经元并且基于第二多个频率仓的内容来触发第二多个神经元。