公开(公告)号：WO2021015896A1

公开(公告)日：2021-01-28

申请号：PCT/US2020/038186

申请日：2020-06-17

Applicant: QUALCOMM INCORPORATED

Inventor： NOORZAD, Parham ,  MALLIK, Siddhartha ,  YOO, Taesang

IPC: H04B7/0413 ,  H04L27/26

Abstract: A machine-learning based multiple-input, multiple-output (MIMO) demapper for a wireless device may include a classifier that selects which MIMO demapper to use for a sample for a particular tone. For example, a wireless device may receive via a plurality of antennas a plurality of signals including a plurality of tones. The wireless device may determine selection features for each tone of the plurality of tones. The wireless device may select, for each tone, by the classifier based on the selection features, a selected demapper from at least a first MIMO demapper and a second MIMO demapper. The second MIMO demapper may have a different performance characteristic than the first MIMO demapper. The wireless device may detect, for each tone, one or more streams using the selected demapper for the tone. A stream may refer to a sequence of bits.

公开(公告)号：WO2021097440A1

公开(公告)日：2021-05-20

申请号：PCT/US2020/060763

申请日：2020-11-16

Applicant: QUALCOMM INCORPORATED

Inventor： LIN, Jamie Menjay ,  YANG, Yang ,  NOORZAD, Parham

IPC: G06N3/04 ,  G06N3/08

Abstract: Aspects described herein provide a method of performing phase selective convolution, including: receiving multi-phase pre-activation activation data; partitioning the multi-phase pre-activation data; applying a first activation function to the set of first phase pre-activation data to form a set of first phase activation output; convolving the set of first phase activation output with a first convolution kernel to form a first phase output feature map; negating the set of second phase activation data; applying a second activation function to the negated set of second phase pre-activation data to form a set of second phase activation output; convolving the set of second phase activation output with a second convolution kernel to form a second phase output feature map; negating the second phase output feature map; and training the neural network based on the first phase output feature map and the second phase output feature map.

公开(公告)号：EP4000184A1

公开(公告)日：2022-05-25

申请号：EP20736859.8

申请日：2020-06-17

Applicant: QUALCOMM INCORPORATED

Inventor： NOORZAD, Parham ,  MALLIK, Siddhartha ,  YOO, Taesang

IPC: H04B7/0413 ,  H04L27/26

公开(公告)号：EP4058941A1

公开(公告)日：2022-09-21

申请号：EP20824003.6

申请日：2020-11-16

Applicant: QUALCOMM Incorporated

Inventor： LIN, Jamie Menjay ,  YANG, Yang ,  NOORZAD, Parham

IPC: G06N3/04 ,  G06N3/08