公开(公告)号：US20240412084A1

公开(公告)日：2024-12-12

申请号：US18262717

申请日：2021-03-12

Applicant: QUALCOMM Incorporated

Inventor： Haijun ZHAO

IPC: G06N5/04 ,  G06F9/50 ,  G06N3/045

Abstract: A method for generating a personalized artificial neural network (ANN) model receives an input at a first artificial neural network. The input is processed to extract a set of intermediate features. The method determines if the input is out-of-distribution relative to a dataset used to train the first artificial neural network. The intermediate features corresponding to the input are provided to a second artificial neural network bases on the out-of-distribution determination. Additionally, the system resources for performing the training and inference tasks of the first artificial neural network and the second, personalized artificial neural network are allocated according to a computational complexity of the training and inference tasks and a power consumption of the resources.

公开(公告)号：US20230169352A1

公开(公告)日：2023-06-01

申请号：US17997307

申请日：2020-06-12

Applicant: Haijun ZHAO ,  QUALCOMM Incorporated

Inventor： Haijun ZHAO

IPC: G06N3/10

CPC classification number: G06N3/10

Abstract: Various embodiments include methods and devices for generating source code of one or more trained machine learning models for use with an existing toolchain of an edge processing device. Embodiments may include parsing a trained machine learning model, generating weight data from the parsed trained machine learning model, generating layer code from the parsed trained machine learning model, and generating a network construct source code of the trained machine learning model from the weight data and the layer code in which the network construct source code is compileable for and executable by the edge processing device.

公开(公告)号：US20190057212A1

公开(公告)日：2019-02-21

申请号：US16080200

申请日：2016-03-01

Applicant: Haijun ZHAO ,  Jilei HOU ,  Liang ZHANG ,  QUALCOMM INCORPORATED

Inventor： Haijun ZHAO ,  Jilei HOU ,  Liang ZHANG

IPC: G06F21/53 ,  G06Q20/38 ,  G06Q20/40

Abstract: Aspects of the disclosure are related to a method, apparatus, and system for using display content from a rich operating system (OS) environment as a background image in a trusted user interface (UI), comprising: capturing a display buffer of the rich OS environment; passing the captured display buffer to a Trusted Application; and displaying, with the Trusted Application, the captured display buffer as the background image in the trusted UI, wherein the Trusted Application is executed in a Trusted Execution Environment (TEE).

公开(公告)号：US20240412075A1

公开(公告)日：2024-12-12

申请号：US18262718

申请日：2021-03-15

Applicant: QUALCOMM Incorporated

Inventor： Haijun ZHAO

IPC: G06N3/096 ,  G06N3/045

Abstract: A method for compressing of a deep neural network model includes determining an architecture of a teacher model. An initial layer of the teacher model is preserved and included in a student model. Repeated layers of the teacher model having a same type are identified. The second of such layers is removed such that the student model includes fewer layers than the teacher model. Knowledge distillation is applied to train the student model. The identifying and removal of layers of the same type is repeated to compress the student model.

公开(公告)号：US20230306274A1

公开(公告)日：2023-09-28

申请号：US18040385

申请日：2020-09-15

Applicant: QUALCOMM Incorporated

Inventor： Haijun ZHAO

IPC: G06N3/10

CPC classification number: G06N3/10

Abstract: Various embodiments include methods and devices for weight layout transformation of a weight tensor. Embodiments may include, accessing a first memory to retrieve weights of the weight tensor in a transformed order that is different than an order for retrieving the weights for a calculation at a network layer of a trained machine learning model, and loading the weights to a second memory in the transformed order. Embodiments may further include retrieving the weights from the second memory in the transformed order, and reordering the weights to the order for implementing the calculation at the network layer of the trained machine learning model.

公开(公告)号：US20170064753A1

公开(公告)日：2017-03-02

申请号：US15119602

申请日：2014-03-26

Applicant: Haijun ZHAO ,  Brian SPENCER ,  QUALCOMM Incorporated

Inventor： Haijun ZHAO ,  Brian SPENCER

IPC: H04W76/02 ,  H04W8/24 ,  H04W8/18 ,  H04W4/00

Abstract: The disclosure is related to searching for a second device to provide a service that a first device is attempting to establish. The first device sends a search profile and a capabilities profile to the second device using near field communication (NFC), the search profile including criteria describing the service the first device is attempting to establish, the capabilities profile including connection capabilities of the first device, receives a score from the second device, the score indicating a closeness of a match between the search profile and the capabilities profile and one or more services and capabilities of the second device, and determines whether to connect with the second device to establish the service based on the received score.

Abstract translation: 本公开涉及搜索第二设备以提供第一设备尝试建立的服务。 第一设备使用近场通信（NFC）向第二设备发送搜索简档和能力简档，搜索简档包括描述第一设备尝试建立的服务的标准，包括第一设备的连接能力的能力简档， 从所述第二设备接收分数，所述得分表示所述搜索简档和所述能力简档之间的匹配的接近度以及所述第二设备的一个或多个服务和能力，并且确定是否与所述第二设备连接以建立所述服务 在收到的分数。

公开(公告)号：US20250103898A1

公开(公告)日：2025-03-27

申请号：US18729859

申请日：2022-03-21

Applicant: QUALCOMM Incorporated

Inventor： Haijun ZHAO

IPC: G06N3/096 ,  G06N3/0455

Abstract: A method of anomaly detection and energy-efficient inference determination includes receiving an input. A set of features of the input are extracted using an artificial neural network (ANN) to generate a latent representation of the input. A reconstruction of the input is generated using the ANN, based on the latent representation. A reconstruction error is computed based on the generated reconstruction and the input. The reconstruction error is compared to a predefined threshold to determine whether the in-distribution data or out-of-distribution data. An anomaly is detected in response to an out-of-distribution determination. A decision model is provided with the latent representation in response to the input being determined to be in-distribution data. In turn, the decision model computes an inference based on the latent representation.

公开(公告)号：US20240232585A1

公开(公告)日：2024-07-11

申请号：US18558978

申请日：2021-07-29

Applicant: QUALCOMM Incorporated

Inventor： Haijun ZHAO

IPC: G06N3/0464 ,  G06N3/09

CPC classification number: G06N3/0464 ,  G06N3/09

Abstract: A method receives a first program code including one or more nested loops. A loop order is determined for the nested loop(s). The determined loop order aligns an input data layout and an output data layout. The nested loop(s) are transformed based on the loop order. A second program code is generated based on the transformed nested loop(s).

公开(公告)号：US20240078425A1

公开(公告)日：2024-03-07

申请号：US18263322

申请日：2021-03-23

Applicant: QUALCOMM Incorporated

Inventor： Haijun ZHAO

IPC: G06N3/08

CPC classification number: G06N3/08

Abstract: A method for energy-efficient classification receiving, via a first circuit, an input data stream from one or more sensors. The first circuit detects, while a second circuit is in a dormant state, if a state change has occurred between a first input of the input data stream and a second input of the input data stream. The second input is a next succeeding input of the input data stream. The first circuit triggers the second circuit to perform a classification of the input data stream in response to detecting the state change.

公开(公告)号：US20220067479A1

公开(公告)日：2022-03-03

申请号：US17274602

申请日：2019-10-08

Applicant: QUALCOMM Incorporated

Inventor： Mingu LEE ,  Wonil CHANG ,  Yeonseok KIM ,  Kyu Woong HWANG ,  Yin HUANG ,  Ruowei WANG ,  Haijun ZHAO ,  Janghoon CHO

IPC: G06N3/02 ,  G01C21/36 ,  G06N7/00

Abstract: Certain aspects of the present disclosure are generally directed to apparatus and techniques for event state detection. One example method generally includes receiving a plurality of sensor signals at a computing device, determining, at the computing device, probabilities of sub-event states based on the plurality of sensor signals using an artificial neural network for each of a plurality of time intervals, and detecting, at the computing device, the event state based on the probabilities of the sub-event states via a state sequence model.