专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明授权

US11586924B2 Determining layer ranks for compression of deep networks 有权
公开(公告)号：US11586924B2
公开(公告)日：2023-02-21
申请号：US15877723
申请日：2018-01-23
申请人： QUALCOMM Incorporated
发明人： Anthony Sarah , Raghuraman Krishnamoorthi
IPC分类号： G06N3/08 , G06N3/084 , G06N3/04
摘要： An apparatus of operating a computational network is configured to determine a low-rank approximation for one or more layers of the computational network based at least in part on a set of residual targets. A set of candidate rank vectors corresponding to the set of residual targets may be determined. Each of the candidate rank vectors may be evaluated using an objective function. A candidate rank vector may be selected and used to determine the low rank approximation. The computational network may be compressed based on the low-rank approximation. In turn the computational network may be operated using the one or more compressed layers.

2. 发明授权

US09305256B2 Automated method for modifying neural dynamics 有权
标题翻译：用于修改神经动力学的自动化方法
公开(公告)号：US09305256B2
公开(公告)日：2016-04-05
申请号：US14066599
申请日：2013-10-29
申请人： QUALCOMM Incorporated
发明人： Anthony Sarah , Robert Howard Kimball
IPC分类号： G06F15/18 , G06N3/08 , G06N3/04 , G06N3/063 , G06N99/00
CPC分类号： G06N3/049 , G06N3/04 , G06N3/063 , G06N3/08 , G06N3/082 , G06N99/005
摘要： A method for improving neural dynamics includes obtaining prototypical neuron dynamics. The method also includes modifying parameters of a neuron model so that the neuron model matches the prototypical neuron dynamics. The neuron dynamics comprise membrane voltages and/or spike timing.
摘要翻译：改进神经动力学的方法包括获得原型神经元动力学。该方法还包括修改神经元模型的参数，使得神经元模型与原型神经元动力学匹配。神经元动力学包括膜电压和/或尖峰定时。

3. 发明授权

US09886663B2 Compiling network descriptions to multiple platforms 有权
公开(公告)号：US09886663B2
公开(公告)日：2018-02-06
申请号：US14085740
申请日：2013-11-20
申请人： QUALCOMM Incorporated
发明人： Anthony Sarah , Robert Howard Kimball , Michael-David Nakayoshi Canoy , Jan Krzys Wegrzyn
IPC分类号： G06N3/10 , G06N3/04
CPC分类号： G06N3/10 , G06N3/049
摘要： A method of generating executable code for a target platform in a neural network includes receiving a spiking neural network description. The method also includes receiving platform-specific instructions for one or more target platforms. Further, the method includes, generating executable code for the target platform(s) based on the platform-specific instructions and the network description.

4. 发明授权

US09542644B2 Methods and apparatus for modulating the training of a neural device 有权
标题翻译：用于调制神经元装置训练的方法和装置
公开(公告)号：US09542644B2
公开(公告)日：2017-01-10
申请号：US14079181
申请日：2013-11-13
申请人： QUALCOMM Incorporated
发明人： Michael-David Nakayoshi Canoy , Yinyin Liu , Anthony Sarah , Adrienne Milner
IPC分类号： G06N3/08 , G06N3/04
CPC分类号： G06N3/08 , G06N3/049
摘要： Methods and apparatus are provided for training a neural device having an artificial nervous system by modulating at least one training parameter during the training. One example method for training a neural device having an artificial nervous system generally includes observing the neural device in a training environment and modulating at least one training parameter based at least in part on the observing. For example, the training apparatus described herein may modify the neural device's internal learning mechanisms (e.g., spike rate, learning rate, neuromodulators, sensor sensitivity, etc.) and/or the training environment's stimuli (e.g., move a flame closer to the device, make the scene darker, etc.). In this manner, the speed with which the neural device is trained (i.e., the training rate) may be significantly increased compared to conventional neural device training systems.
摘要翻译：提供了用于通过在训练期间调制至少一个训练参数来训练具有人造神经系统的神经装置的方法和装置。用于训练具有人造神经系统的神经装置的一个示例性方法通常包括在训练环境中观察神经装置并且至少部分地基于观察来调制至少一个训练参数。例如，本文描述的训练装置可以修改神经装置的内部学习机制（例如，尖峰率，学习速率，神经调节器，传感器灵敏度等）和/或训练环境的刺激（例如，将火焰移动到设备附近，使场景更暗等）。以这种方式，与传统的神经元装置训练系统相比，神经装置训练的速度（即，训练速率）可以显着增加。

5. 发明授权

US09672464B2 Method and apparatus for efficient implementation of common neuron models 有权
公开(公告)号：US09672464B2
公开(公告)日：2017-06-06
申请号：US14267394
申请日：2014-05-01
申请人： QUALCOMM Incorporated
发明人： Anthony Sarah , Jeffrey Alexander Levin , Jeffrey Baginsky Gehlhaar
IPC分类号： G06N3/04 , G06N3/08 , G06N3/10
CPC分类号： G06N3/04 , G06N3/0454 , G06N3/08 , G06N3/10
摘要： 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.

6. 发明授权

US09536190B2 Dynamically assigning and examining synaptic delay 有权
标题翻译：动态分配和检查突触延迟
公开(公告)号：US09536190B2
公开(公告)日：2017-01-03
申请号：US14056856
申请日：2013-10-17
申请人： QUALCOMM Incorporated
发明人： Anthony Sarah , Robert Howard Kimball , Brian Spinar
IPC分类号： G06F15/18 , G06N3/08 , G06N3/04
CPC分类号： G06N3/08 , G06N3/049
摘要： A method for dynamically modifying synaptic delays in a neural network includes initializing a delay parameter and operating the neural network. The method further includes dynamically updating the delay parameter based on a program which is based on a statement including the delay parameter.
摘要翻译：用于动态修改神经网络中的突触延迟的方法包括初始化延迟参数并操作神经网络。该方法还包括基于基于包括延迟参数的语句的程序来动态地更新延迟参数。

7. 发明授权

US10210464B2 Online training for object recognition system 有权
公开(公告)号：US10210464B2
公开(公告)日：2019-02-19
申请号：US14856481
申请日：2015-09-16
申请人： QUALCOMM Incorporated
发明人： David Jonathan Julian , Anthony Sarah
IPC分类号： G06N99/00 , G06K9/00 , G06K9/62 , G06N5/04 , G06N3/02
摘要： A method of online training of a classifier includes determining a distance from one or more feature vectors of an object to a first predetermined decision boundary established during off-line training for the classifier. The method also includes updating a decision rule as a function of the distance. The method further includes classifying a future example based on the updated decision rule.

8. 发明授权

US09600762B2 Defining dynamics of multiple neurons 有权
公开(公告)号：US09600762B2
公开(公告)日：2017-03-21
申请号：US14047885
申请日：2013-10-07
申请人： QUALCOMM Incorporated
发明人： Anthony Sarah , Jeffrey Alexander Levin
IPC分类号： G06N3/063 , G06N3/04
CPC分类号： G06N3/063 , G06N3/049
摘要： A method for dynamically setting a neuron value processes a data structure including a set of parameters for a neuron model and determines a number of segments defined in the set of parameters. The method also includes determining a number of neuron types defined in the set of parameters and determining at least one boundary for a first segment.

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式