公开(公告)号：US20250148769A1

公开(公告)日：2025-05-08

申请号：US18504889

申请日：2023-11-08

Applicant: QUALCOMM Incorporated

Inventor： Alexander BEYKUN ,  Sahil GUPTA ,  Jian WANG ,  Prathamesh Prakash PRABHUDESAI ,  Lin WANG ,  Nathan William LEE ,  Veluppillai ARULESAN ,  Jeffrey Baginsky GEHLHAAR

IPC: G06V10/82 ,  G05D1/08 ,  G06V20/58

Abstract: Certain aspects provide techniques and apparatuses for efficient operation of a machine learning model based on partitioning the machine learning model. An example method generally includes receiving a graph for a machine learning model. The graph for the machine learning model generally includes a plurality of subgraphs representing different portions of the machine learning model. The machine learning model is instantiated across a plurality of process domains associated with a same application based on the plurality of subgraphs in the graph for the machine learning model. An inference is generated based on executing the machine learning model across the plurality of process domains, and one or more actions are taken based on the generated inference.

公开(公告)号：US20240362468A1

公开(公告)日：2024-10-31

申请号：US18543533

申请日：2023-12-18

Applicant: QUALCOMM Incorporated

Inventor： Mingu LEE ,  Christopher LOTT ,  Joseph Binamira SORIAGA ,  Jilei HOU ,  Muralidhar Reddy AKULA ,  Jeffrey Baginsky GEHLHAAR

IPC: G06N3/0475

CPC classification number: G06N3/0475

Abstract: Certain aspects of the present disclosure provide techniques and apparatus for generating a response to an input query using a generative artificial intelligence model. An example method generally includes receiving an input for processing. A prompt representing the received input is generated based on the received input, contextual information associated with the received prompt, and a prompt-generating artificial intelligence model. The generated prompt is output to a generative artificial intelligence model for processing. A response to the generated prompt is received from the generative artificial intelligence model and output as a response to the received input.

公开(公告)号：US20150248607A1

公开(公告)日：2015-09-03

申请号：US14267394

申请日：2014-05-01

Applicant: QUALCOMM Incorporated

Inventor： Anthony SARAH ,  Jeffrey Alexander LEVIN ,  Jeffrey Baginsky GEHLHAAR

IPC: G06N3/04 ,  G06N3/08

CPC classification number: G06N3/04 ,  G06N3/0454 ,  G06N3/08 ,  G06N3/10

Abstract: Certain aspects of the present disclosure support efficient implementation of common neuron models. In an aspect, a first memory layout can be allocated for parameters and state variables of instances of a first neuron model, and a second memory layout different from the first memory layout can be allocated for parameters and state variables of instances of a second neuron model having a different complexity than the first neuron model.

Abstract translation: 本公开的某些方面支持有效实施普通神经元模型。 在一方面，可以为第一神经元模型的实例的参数和状态变量分配第一存储器布局，并且可以为不同于第一存储器布局的第二存储器布局分配用于第二神经元模型的实例的参数和状态变量 具有与第一神经元模型不同的复杂性。

公开(公告)号：US20150088796A1

公开(公告)日：2015-03-26

申请号：US14268152

申请日：2014-05-02

Applicant: QUALCOMM INCORPORATED

Inventor： David Jonathan JULIAN ,  Jeffrey Alexander LEVIN ,  Jeffrey Baginsky GEHLHAAR

IPC: G06N3/04 ,  G06N3/08

CPC classification number: G06N3/049 ,  G06N3/0454

Abstract: Certain aspects of the present disclosure support assigning neurons and/or synapses to group tags where group tags have an associated set of parameters. By using group tags, neurons or synapses in a population can be assigned a group tag. Then, by changing a parameter associated with the group tag, all synapses or neurons in the group may have that parameter changed.

Abstract translation: 本公开的某些方面支持将神经元和/或突触分配给组标签，其中组标签具有相关联的参数集合。 通过使用组标签，群体中的神经元或突触可以被分配一个组标签。 然后，通过更改与组标签相关联的参数，组中的所有突触或神经元可能会改变该参数。