公开(公告)号：US20230376753A1

公开(公告)日：2023-11-23

申请号：US18157723

申请日：2023-01-20

Applicant: QUALCOMM Incorporated

Inventor： Seokeon CHOI ,  Sungha CHOI ,  Seunghan YANG ,  Hyunsin PARK ,  Debasmit DAS ,  Sungrack YUN

IPC: G06N3/08

CPC classification number: G06N3/08

Abstract: Systems and techniques are provided for training a neural network model or machine learning model. For example, a method of augmenting training data can include augmenting, based on a randomly initialized neural network, training data to generate augmented training data and aggregating data with a plurality of styles from the augmented training data to generate aggregated training data. The method can further include applying semantic-aware style fusion to the aggregated training data to generate fused training data and adding the fused training data as fictitious samples to the training data to generate updated training data for training the neural network model or machine learning model.

公开(公告)号：US20230281509A1

公开(公告)日：2023-09-07

申请号：US18086586

申请日：2022-12-21

Applicant: QUALCOMM Incorporated

Inventor： Sungha CHOI ,  Seunghan YANG ,  Seokeon CHOI ,  Sungrack YUN

IPC: G06N20/00

CPC classification number: G06N20/00

Abstract: A processor-implemented method includes training a machine learning model on a source domain. The method also includes testing the machine learning model on a target domain, after training. The method further includes training the machine learning model on the target domain by regularizing weights of the machine learning model such that shift-agnostic weights are subjected to a higher penalty than shift-biased weights.

公开(公告)号：US20230081012A1

公开(公告)日：2023-03-16

申请号：US17474679

申请日：2021-09-14

Applicant: QUALCOMM Incorporated

Inventor： Kyu Woong HWANG ,  Sungrack YUN ,  Jaewon CHOI ,  Seunghan YANG ,  Janghoon CHO ,  Hyoungwoo PARK ,  Hanul KIM

IPC: H04W12/02 ,  H04W64/00 ,  G06F21/62

Abstract: Embodiments include methods of assisting a user in locating a mobile device executed by a processor of the mobile device. Various embodiments may include a processor of a mobile device obtaining information useful for locating the mobile device from a sensor of the mobile device configured to obtain information regarding surroundings of the mobile device, anonymizing the obtained information to remove private information, and uploading the anonymized information to a remote server in response to determining that the mobile device may be misplaced. Anonymizing the obtained information may include removing speech from an audio input and compiling samples of ambient noise for inclusion in the anonymized information. Anonymizing the obtained information to remove private information includes editing an image captured by the mobile device to make images of detected individuals unrecognizable.

公开(公告)号：US20250077313A1

公开(公告)日：2025-03-06

申请号：US18459239

申请日：2023-08-31

Applicant: QUALCOMM Incorporated

Inventor： Simyung CHANG ,  Kyu Woong HWANG ,  Juntae LEE ,  Kyuhong SHIM ,  Jihwan BANG ,  Seunghan YANG ,  Jaeseong YOU ,  Minseop PARK ,  Christopher LOTT

IPC: G06F9/54 ,  G06F9/48

Abstract: A processor-implemented method for generating a default adapter for context switching includes analyzing a first neural network model and one or more adapters. The first neural network model is pre-trained and each of the adapters is configured with an architecture and parameters for performing a different downstream task of a set of downstream tasks. A default adapter is defined based on a capacity of the one or more adapters. The default adapter is applied to one or more layers of the first neural network model during a context switch to a replace one of the adapters for a different task. A graph corresponding to the first neural network model is unchanged.

公开(公告)号：US20240104420A1

公开(公告)日：2024-03-28

申请号：US17935067

申请日：2022-09-23

Applicant: QUALCOMM Incorporated

Inventor： Kyu Woong HWANG ,  Seunghan YANG ,  Hyunsin PARK ,  Leonid SHEYNBLAT ,  Vinesh SUKUMAR ,  Ziad ASGHAR ,  Justin MCGLOIN ,  Joel LINSKY ,  Tong TANG

IPC: G06N20/00 ,  G06K9/62 ,  G06N5/04

CPC classification number: G06N20/00 ,  G06K9/6218 ,  G06N5/04

Abstract: Certain aspects of the present disclosure provide techniques and apparatus for a training and using machine learning models in multi-device network environments. An example computer-implemented method for network communications performed by a host device includes extracting a feature set from a data set associated with a client device using a client-device-specific feature extractor, wherein the feature set comprises a subset of features in a common feature space, training a task-specific model based on the extracted feature set and one or more other feature sets associated with other client devices, wherein the feature sets associated with the other client devices comprise one or more subsets of features in the common feature space, and deploying, to each respective client device of a plurality of client devices, a respective version of the task-specific model.

公开(公告)号：US20220368856A1

公开(公告)日：2022-11-17

申请号：US17320627

申请日：2021-05-14

Applicant: QUALCOMM Incorporated

Inventor： Jae-Won CHOI ,  Sungrack YUN ,  Janghoon CHO ,  Hanul KIM ,  Hyoungwoo PARK ,  Seunghan YANG ,  Kyu Woong HWANG

IPC: H04N7/15 ,  G06K9/00

Abstract: Embodiment systems and methods for presenting a facial expression in a virtual meeting may include detecting a user facial expression of a user based on information received from a sensor of the computing device, determining whether the detected user facial expression is approved for presentation on an avatar in a virtual meeting, generating an avatar exhibiting a facial expression consistent with the detected user facial expression in response to determining that the detected user facial expression is approved for presentation on an avatar in the virtual meeting, generating an avatar exhibiting a facial expression that is approved for presentation in response to determining that the detected user facial expression is not approved for presentation on an avatar in the virtual meeting, and presenting the generated avatar in the virtual meeting.

公开(公告)号：US20240185078A1

公开(公告)日：2024-06-06

申请号：US18456112

申请日：2023-08-25

Applicant: QUALCOMM Incorporated

Inventor： Simyung CHANG ,  Byeonggeun KIM ,  Seunghan YANG ,  Kyuhong SHIM

IPC: G06N3/088 ,  G06N3/04

CPC classification number: G06N3/088 ,  G06N3/04

Abstract: A processor-implement method includes generating, for each input of a group of inputs, a clean sample and an augmented sample. The method also includes associating, for each input of the group of inputs, the clean sample with the augmented sample to form a positive pair. The method further includes associating, for each input of the group of inputs, the clean sample with another clean sample associated with another input of the group of inputs to form a negative pair. The method still further includes learning one or more representations of the group of inputs based on the positive pair and the negative pair of each input of the group of inputs.

公开(公告)号：US20240112039A1

公开(公告)日：2024-04-04

申请号：US18238998

申请日：2023-08-28

Applicant: QUALCOMM Incorporated

Inventor： Seunghan YANG ,  Seokeon CHOI ,  Hyunsin PARK ,  Sungha CHOI ,  Sungrack YUN

IPC: G06N3/098 ,  H04L67/10

CPC classification number: G06N3/098 ,  H04L67/10

Abstract: Example implementations include methods, apparatuses, and computer-readable mediums of federated learning by a federated client device, comprising identifying client invariant information of a neural network for performing a machine learning (ML) task in a first domain known to a federated server. The implementations further comprising transmitting the client invariant information to the federated server, the federated server configured to generate a ML model for performing the ML task in a domain unknown to the federated server based on the client invariant information and other client invariant information of another neural network for performing the ML task in a second domain known to the federated server.

公开(公告)号：US20230119791A1

公开(公告)日：2023-04-20

申请号：US17937765

申请日：2022-10-03

Applicant: QUALCOMM Incorporated

Inventor： Byeonggeun KIM ,  Seunghan YANG ,  Hyunsin PARK ,  Juntae LEE ,  Simyung CHANG

IPC: G10L21/034 ,  G10L17/18 ,  G10L25/30 ,  G10L25/51 ,  G10L17/04

Abstract: Techniques and apparatus for training a neural network to classify audio into one of a plurality of categories and using such a trained neural network. An example method generally includes receiving a data set including a plurality of audio samples. A relaxed feature-normalized data set is generated by normalizing each audio sample of the plurality of audio samples. A neural network is trained to classify audio into one of a plurality of categories based on the relaxed feature-normalized data set, and the trained neural network is deployed.

公开(公告)号：US20250136144A1

公开(公告)日：2025-05-01

申请号：US18499584

申请日：2023-11-01

Applicant: QUALCOMM Incorporated

Inventor： Seunghan YANG ,  Simyung CHANG ,  Minseop PARK ,  Jinkyu LEE

IPC: B60W60/00

Abstract: Various embodiments may include methods, systems, and devices enabling a vehicle equipped with a complex sensor system encompassing low-end sensors of the second class of vehicles to train a low-end self-driving system. Various embodiments may include a processing system of the vehicle training the low-end self-driving system based on differences between outputs of a low-end self-driving sensor processing model generated based on the low-end sensors to outputs of a complex sensor processing model of the vehicle based on the vehicles complex sensor system. At least a portion of the trained self-driving system for the second class of vehicles may be provided to a remote server for deployment in the second class of vehicles.