公开(公告)号：US09177245B2

公开(公告)日：2015-11-03

申请号：US13763005

申请日：2013-02-08

Applicant: QUALCOMM TECHNOLOGIES INC.

Inventor： Micah Richert ,  Filip Piekniewski ,  Eugene Izhikevich ,  Sach Sokol ,  Victor Hokkiu Chan ,  Jeffrey Alexander Levin

IPC: G06N3/08 ,  G06N3/04

CPC classification number: G06K9/00711 ,  G06K9/4671 ,  G06N3/049 ,  G06N3/08 ,  G06T7/246 ,  G06T2207/10016

Abstract: Apparatus and methods for learning in response to temporally-proximate features. In one implementation, an image processing apparatus utilizes bi-modal spike timing dependent plasticity in a spiking neuron network. Based on a response by the neuron to a frame of input, the bi-modal plasticity mechanism is used to depress synaptic connections delivering the present input frame and to potentiate synaptic connections delivering previous and/or subsequent frames of input. The depression of near-contemporaneous input prevents the creation of a positive feedback loop and provides a mechanism for network response normalization.

Abstract translation: 响应于时间上接近的特征学习的装置和方法。 在一个实施方案中，图像处理装置在加标神经元网络中利用双模态尖峰时间相关可塑性。 基于神经元对输入帧的响应，双模式可塑性机制用于抑制递送当前输入帧的突触连接并且加强递送先前和/或后续输入帧的突触连接。 近同期输入的抑制阻止了正反馈回路的创建，并提供了网络响应归一化的机制。

公开(公告)号：US20150256486A1

公开(公告)日：2015-09-10

申请号：US14720947

申请日：2015-05-25

Applicant: QUALCOMM Technologies Inc.

Inventor： Philippe BOUCARD ,  Jean-Jacques LECLER

IPC: H04L12/935 ,  H04L29/06 ,  H04L12/933

CPC classification number: H04L49/3072 ,  G06F13/4009 ,  G06F2213/0038 ,  H04L45/245 ,  H04L47/10 ,  H04L49/109 ,  H04L69/22 ,  Y02B70/30 ,  Y02D50/30

Abstract: Packet format configurability is extended for packets transported on physical links of an Intellectual Property (IP) core interconnect by using at least two independent parameters: one parameter governing data-width and one parameter governing latency penalty. The at least two independent parameters allow creation of transport protocol packets without additional latency insertion, which is useful for low-latency applications. The at least two independent parameters also allow creation of narrow packets with multi-cycle additional latency, which is useful for latency tolerant, area sensitive applications.

Abstract translation: 通过使用至少两个独立参数：一个控制数据宽度的参数和一个控制延迟处罚的参数的参数，扩展了对于在知识产权（IP）核心互连的物理链路上传输的数据包的数据包格式可配置性。 至少两个独立参数允许创建传输协议分组，而不需要额外的延迟插入，这对于低延迟应用是有用的。 至少两个独立参数还允许创建具有多周期附加延迟的窄分组，这对延迟容忍的区域敏感应用是有用的。

公开(公告)号：US20150181115A1

公开(公告)日：2015-06-25

申请号：US14574150

申请日：2014-12-17

Applicant: QUALCOMM TECHNOLOGIES, INC.

Inventor： Ayelet MASHIAH

IPC: H04N5/232 ,  H04N5/262 ,  G06T7/20

CPC classification number: H04N5/23238 ,  G06T3/4038 ,  G06T7/248 ,  G06T2207/10016 ,  G06T2207/20021 ,  H04N5/225 ,  H04N5/2624

Abstract: A system, method, and computer program product for selecting qualifying frames from an image sequence for use in subsequent stitching into a composite panoramic image are disclosed. Incoming frames from any source may be cropped and downscaled prior to evaluation against qualifying criteria relating to image overlap and local motion. Qualifying images are saved and/or output. The resulting panoramic image generally uses fewer qualifying images and appears smoother and has fewer artifacts than those of the prior art. The qualifying criterion for image overlap is a predetermined overlap margin or percentage between a current image and a previous image from the sequence. The qualifying criterion for image motion includes a maximum amount of local motion, often due to passing objects. The embodiments may process incoming images in real time or from stored sequences. Problems may trigger user warnings.

Abstract translation: 公开了一种用于从用于随后拼接成复合全景图像的图像序列中选择合格帧的系统，方法和计算机程序产品。 在对与图像重叠和局部运动有关的限定标准进行评估之前，来自任何来源的进帧可以被裁剪和缩小。 合格图像被保存和/或输出。 所得到的全景图像通常使用较少的限定图像，并且看起来更平滑并且具有比现有技术更少的伪影。 图像重叠的限定条件是当前图像与来自该序列的先前图像之间的预定重叠余量或百分比。 图像运动的限定标准包括局部运动的最大量，这通常是由于传递的对象。 这些实施例可以实时地或从存储的序列处理输入的图像。 问题可能会触发用户警告。

公开(公告)号：US20250103882A1

公开(公告)日：2025-03-27

申请号：US18583291

申请日：2024-02-21

Applicant: QUALCOMM Technologies, Inc.

Inventor： Dawid Jan KOPICZKO ,  Yuki Markus ASANO ,  Tijmen Pieter Frederik BLANKEVOORT

IPC: G06N3/08

Abstract: Certain aspects of the present disclosure provide techniques and apparatus for efficiently adapting a machine learning model from a base task to a downstream task based on frozen matrices. An example method generally includes receiving an input for processing through a layer of a neural network. An output of the layer of the neural network is generated based on a first product, the first product being based on a first trainable scaling vector, a first frozen matrix, a second trainable scaling vector, a second frozen matrix, and the received input.

公开(公告)号：US20250103305A1

公开(公告)日：2025-03-27

申请号：US18538895

申请日：2023-12-13

Applicant: QUALCOMM Technologies, Inc.

Inventor： Natasha BUTT ,  Auke Joris WIGGERS ,  Corrado RAINONE ,  Blazej Jakub Manczak ,  Taco Sebastiaan Cohen

IPC: G06F8/35

Abstract: Systems and techniques are described for providing iterative policy-guided program synthesis. For example, a device may generate, based on a policy that receives input-output data of one or more tasks as input, a first set of programs, add the first set of programs and the input-output data to the training dataset to generate an updated training dataset, train the policy based on the first set of programs and the input-output data to generate an updated policy, identify, based on the updated policy, a second set of programs for second input-output data for a second set of tasks, add the second set of programs and second input-output data to the updated training dataset to generate a second updated training dataset; and train the updated policy based on the second set of programs and the second input-output data to generate a second updated policy.

公开(公告)号：US20250086522A1

公开(公告)日：2025-03-13

申请号：US18462914

申请日：2023-09-07

Applicant: Qualcomm Technologies, Inc.

Inventor： Lars VEEFKIND ,  Gabriele CESA

IPC: G06N20/20

Abstract: Certain aspects of the present disclosure provide techniques and apparatus for improved machine learning. A set of training data is accessed, and a transformation group comprising a plurality of group elements is determined. A set of unconstrained weights for a layer of the machine learning model is generated based on the set of training data. A set of parameter values for a likelihood function for the layer is generated based on the set of training data. A set of constrained weights is generated, based at least in part on the likelihood function and the set of unconstrained weights, such that the set of constrained weights is equivariant with respect to at least a subset of the plurality of group elements.

公开(公告)号：US20250005336A1

公开(公告)日：2025-01-02

申请号：US18710150

申请日：2023-01-24

Applicant: QUALCOMM TECHNOLOGIES, INC.

Inventor： Phillip LIPPE ,  Yuki Markus ASANO ,  Sara MAGLIACANE ,  Taco Sebastiaan COHEN ,  Efstratios GAVVES

IPC: G06N3/0475 ,  G06V10/82

Abstract: A processor-implemented method for causal representation learning of temporal effects includes receiving, via an artificial neural network (ANN), temporal sequence data for high-dimensional observations. The ANN generates a latent representation based on latent variables for the temporal sequence data. The latent variables of the temporal sequence data are assigned to causal variables. The ANN determines a representation of causal factors for each dimension of the temporal sequence databased on the assignment.

公开(公告)号：US12142577B2

公开(公告)日：2024-11-12

申请号：US17191550

申请日：2021-03-03

Applicant: QUALCOMM Technologies Inc. ,  RF360 Europe GmbH

Inventor： Marc Huesgen ,  Philipp Michael Jaeger

IPC: H01L23/552 ,  H01L21/48 ,  H01L21/56 ,  H01L21/768 ,  H01L23/367 ,  H01L23/373 ,  H01L23/48 ,  H01L23/49

Abstract: A package that includes a substrate, an integrated device coupled to the substrate, an encapsulation layer located over the substrate, at least one encapsulation layer interconnect located in the encapsulation layer, and a metal layer located over the encapsulation layer. The substrate includes at least one dielectric layer and a plurality of interconnects. The encapsulation layer interconnect is coupled to the substrate. The metal layer is configured as an electromagnetic interference (EMI) shield for the package. The metal layer is located over a backside of the integrated device.

公开(公告)号：US20240233365A9

公开(公告)日：2024-07-11

申请号：US17769269

申请日：2020-11-14

Applicant: QUALCOMM Technologies, Inc.

Inventor： Mert KILICKAYA ,  Noureldien Mahmoud Elsayed HUSSEIN ,  Efstratios GAVVES ,  Arnold Wilhelmus Maria SMEULDERS

IPC: G06V20/52 ,  G06V10/75 ,  G06V10/764 ,  G06V10/778 ,  G06V10/80 ,  G06V10/82

CPC classification number: G06V20/52 ,  G06V10/751 ,  G06V10/764 ,  G06V10/778 ,  G06V10/806 ,  G06V10/82 ,  G06V40/10

Abstract: A method for classifying a human-object interaction includes identifying a human-object interaction in the input. Context features of the input are identified. Each identified context feature is compared with the identified human-object interaction. An importance of the identified context feature is determined for the identified human-object interaction. The context feature is fused with the identified human-object interaction when the importance is greater than a threshold.

公开(公告)号：US12010488B2

公开(公告)日：2024-06-11

申请号：US18126938

申请日：2023-03-27

Applicant: Qualcomm Technologies Inc.

Inventor： Robert J. Littrell

IPC: H04R29/00 ,  G10L25/18 ,  G10L25/21 ,  G10L25/78 ,  H04R17/02 ,  H04R19/04

CPC classification number: H04R29/004 ,  G10L25/18 ,  G10L25/21 ,  G10L25/78 ,  H04R17/02 ,  H04R19/04 ,  H04R2201/003

Abstract: An acoustic device is described and includes an acoustic sensor element configured to sense acoustic energy and produce an output signal and a threshold detector circuit including a switch having an input coupled to the output of the acoustic sensor element to receive the output signal, a control port that receives a control signal, and first and second output ports, a first channel including an analog-to-digital converter that operates at a first power level a second analog-to-digital converter that operates at a second higher power level, relative to the first power level and a threshold level detector that receives an output from the first analog-to-digital converter to produce the control signal having a first state that causes the switch feed the output signal from the acoustic sensor element to the second analog-to-digital converter when the first digitized output signal meets a threshold criteria.