公开(公告)号：US11704571B2

公开(公告)日：2023-07-18

申请号：US17067233

申请日：2020-10-09

Applicant: QUALCOMM Incorporated

Inventor： Kambiz Azarian Yazdi ,  Tijmen Pieter Frederik Blankevoort ,  Jin Won Lee ,  Yash Sanjay Bhalgat

IPC: G06N3/08 ,  G06N3/082 ,  G06N3/04

CPC classification number: G06N3/082 ,  G06N3/04

Abstract: A method for pruning weights of an artificial neural network based on a learned threshold includes determining a pruning threshold for pruning a first set of pre-trained weights of multiple pre-trained weights based on a function of a classification loss and a regularization loss. Weights are pruned from the first set of pre-trained weights when a first value of the weight is less than the pruning threshold. A second set of pre-trained weights of the multiple pre-trained weights is fine-tuned or adjusted in response to a second value of each pre-trained weight in the second set of pre-trained weights being greater than the pruning threshold.

公开(公告)号：US20220391702A1

公开(公告)日：2022-12-08

申请号：US17805021

申请日：2022-06-01

Applicant: QUALCOMM Incorporated

Inventor： Jamie Menjay LIN ,  Yash Sanjay Bhalgat ,  Edwin Chongwoo Park

IPC: G06N3/08 ,  G06N3/04 ,  G06F9/345

Abstract: Certain aspects of the present disclosure provide techniques for kernel expansion. An input data tensor is received at a first layer in a neural network, and a first convolution is performed for a first kernel, where the first kernel has a size greater than a preferred size. Performing the first convolution comprises generating a plurality of intermediate tensors by performing a plurality of intermediate convolutions using a plurality of intermediate kernels with a size of the preferred size, and accumulating the plurality of intermediate tensors to generate an output tensor for the first convolution.

公开(公告)号：US12136038B2

公开(公告)日：2024-11-05

申请号：US17175487

申请日：2021-02-12

Applicant: QUALCOMM Incorporated

Inventor： Yash Sanjay Bhalgat ,  Jin Won Lee ,  Jamie Menjay Lin ,  Fatih Murat Porikli ,  Chirag Sureshbhai Patel

IPC: G06N3/082 ,  G06F18/214 ,  G06N3/098 ,  G06N20/00

Abstract: Certain aspects of the present disclosure provide techniques for improved machine learning using gradient pruning, comprising computing, using a first batch of training data, a first gradient tensor comprising a gradient for each parameter of a parameter tensor for a machine learning model; identifying a first subset of gradients in the first gradient tensor based on a first gradient criteria; and updating a first subset of parameters in the parameter tensor based on the first subset of gradients in the first gradient tensor.

公开(公告)号：US11908155B2

公开(公告)日：2024-02-20

申请号：US17203607

申请日：2021-03-16

Applicant: QUALCOMM Incorporated

Inventor： John Yang ,  Yash Sanjay Bhalgat ,  Fatih Murat Porikli ,  Simyung Chang

IPC: G06F18/213 ,  G06N20/00 ,  G06T7/70

CPC classification number: G06T7/70 ,  G06F18/213 ,  G06N20/00 ,  G06T2207/20081

Abstract: Certain aspects of the present disclosure provide a method, including: processing input data with a feature extraction stage of a machine learning model to generate a feature map; applying an attention map to the feature map to generate an augmented feature map; processing the augmented feature map with a refinement stage of the machine learning model to generate a refined feature map; processing the refined feature map with a first regression stage of the machine learning model to generate multi-dimensional task output data; and processing the refined feature data with an attention stage of the machine learning model to generate an updated attention map.