-
公开(公告)号:WO2023086912A1
公开(公告)日:2023-05-19
申请号:PCT/US2022/079680
申请日:2022-11-11
Applicant: QUALCOMM INCORPORATED
Inventor: KADAMBI, Shreya , BEHBOODI, Arash , SORIAGA, Joseph, Binamira , WELLING, Max
Abstract: Certain aspects of the present disclosure provide methods, apparatus, and systems for predicting a location of a device in a spatial environment using a machine learning model. An example method generally includes measuring a plurality of signals received from a network entity at a device. A channel state information (CSI) measurement is generated from the measured plurality of signals. Generally, the CSI measurement includes a multipath component. Positions of one or more anchors in a spatial environment are identified based on a machine learning model trained to identify the positions of the one or more anchors based on the CSI measurement. A location of the device is estimated based on the identified positions of the one or more anchors.
-
公开(公告)号:WO2022232716A2
公开(公告)日:2022-11-03
申请号:PCT/US2022/070537
申请日:2022-02-04
Applicant: QUALCOMM INCORPORATED
Inventor: BONDESAN, Roberto , WELLING, Max
IPC: G06N10/40 , G06N3/04 , G06N10/60 , G06N3/0464
Abstract: Certain aspects of the present disclosure provide techniques for performing probabilistic convolution operation with a quantum and non-quantum processing systems.
-
公开(公告)号:WO2022072863A1
公开(公告)日:2022-04-07
申请号:PCT/US2021/053219
申请日:2021-10-01
Applicant: QUALCOMM INCORPORATED
Inventor: FINZI, Marc Anton , BONDESAN, Roberto , WELLING, Max
IPC: G06N3/04
Abstract: Certain aspects of the present disclosure provide techniques for performing operations with probabilistic numeric convolutional neural network, including: defining a Gaussian Process based on a mean and a covariance of input data; applying a linear operator to the Gaussian Process to generate pre-activation data; applying a nonlinear operation to the pre-activation data to form activation data; and applying a pooling operation to the activation data to generate an inference.
-
公开(公告)号:WO2021050590A1
公开(公告)日:2021-03-18
申请号:PCT/US2020/049997
申请日:2020-09-09
Applicant: QUALCOMM INCORPORATED
Inventor: REISSER, Matthias , PITRE, Saurabh Kedar , ZHU, Xiaochun , TEAGUE, Edward Harris , WANG, Zhongze , WELLING, Max
Abstract: In one embodiment, a method of simulating an operation of an artificial neural network on a binary neural network processor includes receiving a binary input vector for a layer including a probabilistic binary weight matrix and performing vector-matrix multiplication of the input vector with the probabilistic binary weight matrix, wherein the multiplication results are modified by simulated binary-neural-processing hardware noise, to generate a binary output vector, where the simulation is performed in the forward pass of a training algorithm for a neural network model for the binary-neural-processing hardware.
-
公开(公告)号:EP4295272A1
公开(公告)日:2023-12-27
申请号:EP22704257.9
申请日:2022-01-21
Applicant: QUALCOMM INCORPORATED
-
26.
公开(公告)号:EP4229557A1
公开(公告)日:2023-08-23
申请号:EP21806901.1
申请日:2021-10-19
Applicant: QUALCOMM INCORPORATED
Inventor: BEHBOODI, Arash , ZHENG, Simeng , SORIAGA, Joseph Binamira , WELLING, Max , OREKONDY, Tribhuvanesh
-
27.
公开(公告)号:EP4204841A2
公开(公告)日:2023-07-05
申请号:EP21790638.7
申请日:2021-08-31
Applicant: QUALCOMM Incorporated
-
28.
公开(公告)号:EP4028956A1
公开(公告)日:2022-07-20
申请号:EP20776002.6
申请日:2020-09-08
Applicant: QUALCOMM INCORPORATED
Inventor: WANG, Zhongze , TEAGUE, Edward , WELLING, Max
-
公开(公告)号:EP3420491B1
公开(公告)日:2019-06-26
申请号:EP17722644.6
申请日:2017-04-28
Applicant: Qualcomm Incorporated
Inventor: PARK, Mijung , WELLING, Max
-
公开(公告)号:EP3420491A1
公开(公告)日:2019-01-02
申请号:EP17722644.6
申请日:2017-04-28
Applicant: Qualcomm Incorporated
Inventor: PARK, Mijung , WELLING, Max
CPC classification number: G06N20/00 , G06F17/00 , G06F17/11 , G06F21/6254
Abstract: A method for privatizing an iteratively reweighted least squares (IRLS) solution includes perturbing a first moment of a dataset by adding noise and perturbing a second moment of the dataset by adding noise. The method also includes obtaining the IRLS solution based on the perturbed first moment and the perturbed second moment. The method further includes generating a differentially private output based on the IRLS solution.
-
-
-
-
-
-
-
-
-