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

US09449270B2 Implementing structural plasticity in an artificial nervous system 有权
标题翻译：在人造神经系统中实施结构可塑性
公开(公告)号：US09449270B2
公开(公告)日：2016-09-20
申请号：US14157143
申请日：2014-01-16
申请人： QUALCOMM Incorporated , Nina Marcos
发明人： Jason Frank Hunzinger , Michael-David Nakayoshi Canoy , Paul Edward Bender , Victor Hokkiu Chan , Gina Marcela Escobar Mora
IPC分类号： G06F15/18 , G06N3/08 , G06N3/04
CPC分类号： G06N3/04 , G06N3/049 , G06N3/08 , G06N3/082
摘要： Methods and apparatus are provided for implementing structural plasticity in an artificial nervous system. One example method for altering a structure of an artificial nervous system generally includes determining a synapse in the artificial nervous system for reassignment, determining a first artificial neuron and a second artificial neuron for connecting via the synapse, and reassigning the synapse to connect the first artificial neuron with the second artificial neuron. Another example method for operating an artificial nervous system, generally includes determining a synapse in the artificial nervous system for assignment; determining a first artificial neuron and a second artificial neuron for connecting via the synapse, wherein at least one of the synapse or the first and second artificial neurons are determined randomly or pseudo-randomly; and assigning the synapse to connect the first artificial neuron with the second artificial neuron.
摘要翻译：提供了在人造神经系统中实现结构可塑性的方法和装置。用于改变人造神经系统的结构的一个示例性方法通常包括确定用于重新分配的人造神经系统中的突触，确定第一人造神经元和第二人造神经元以经由突触连接，以及重新分配突触以连接第一人工神经元神经元与第二个人造神经元。用于操作人造神经系统的另一示例性方法通常包括确定用于分配的人造神经系统中的突触; 确定经由所述突触连接的第一人造神经元和第二人造神经元，其中所述突触或所述第一和第二人造神经元中的至少一个被随机地或伪随机地确定; 并分配突触将第一人工神经元与第二人造神经元连接。

2. 发明授权

US09460382B2 Neural watchdog 有权
标题翻译：神经看门狗
公开(公告)号：US09460382B2
公开(公告)日：2016-10-04
申请号：US14139732
申请日：2013-12-23
申请人： QUALCOMM Incorporated , Nina Marcos
发明人： Michael-David Nakayoshi Canoy , Jason Frank Hunzinger
IPC分类号： G06N3/04
CPC分类号： G06N3/049
摘要： A method of monitoring a neural network includes monitoring activity of the neural network. The method also includes detecting a condition based on the activity. The method further includes performing an exception event based on the detected condition.
摘要翻译：监测神经网络的方法包括监测神经网络的活动。该方法还包括基于活动来检测条件。该方法还包括基于检测到的条件执行异常事件。

3. 发明授权

US09418332B2 Post ghost plasticity 有权
标题翻译：后鬼可塑性
公开(公告)号：US09418332B2
公开(公告)日：2016-08-16
申请号：US14167752
申请日：2014-01-29
申请人： QUALCOMM Incorporated , Nina Marcos
发明人： Jason Frank Hunzinger , Jeffrey Alexander Levin
IPC分类号： G06F15/18 , G06N3/08 , G06N3/04
CPC分类号： G06N3/049 , G06N3/04
摘要： Methods and apparatus are provided for inferring and accounting for missing post-synaptic events (e.g., a post-synaptic spike that is not associated with any pre-synaptic spikes) at an artificial neuron and adjusting spike-timing dependent plasticity (STDP) accordingly. One example method generally includes receiving, at an artificial neuron, a plurality of pre-synaptic spikes associated with a synapse, tracking a plurality of post-synaptic spikes output by the artificial neuron, and determining at least one of the post-synaptic spikes is associated with none of the plurality of pre-synaptic spikes. According to certain aspects, determining inferring missing post-synaptic events may be accomplished by using a flag, counter, or other variable that is updated on post-synaptic firings. If this post-ghost variable changes between pre-synaptic-triggered adjustments, then the artificial nervous system can determine there was a missing post-synaptic pairing.
摘要翻译：提供了用于推断和计算在人造神经元处丢失的突触后事件（例如，与突触前尖峰之间不相关的突触后尖峰）并相应地调整尖峰时序依赖性可塑性（STDP）的方法和装置。一个示例性方法通常包括在人造神经元处接收与突触相关联的多个突触前尖峰，跟踪由人造神经元输出的多个突触后尖峰，并且确定突触后尖峰中的至少一个是与多个突触前尖峰中的任一个相关联。根据某些方面，确定推断缺失的突触后事件可以通过使用在突触后发射上更新的标志，计数器或其他变量来实现。如果这个后幽灵变量在突触前触发的调整之间变化，则人造神经系统可以确定缺少突触后配对。

4. 发明申请

US20140074761A1 DYNAMICAL EVENT NEURON AND SYNAPSE MODELS FOR LEARNING SPIKING NEURAL NETWORKS 审中-公开
标题翻译：动态事件神经元和学习模拟神经网络
公开(公告)号：US20140074761A1
公开(公告)日：2014-03-13
申请号：US14081777
申请日：2013-11-15
申请人： QUALCOMM Incorporated
发明人： Jason Frank Hunzinger
IPC分类号： G06N3/02
CPC分类号： G06N3/02 , G06N3/049
摘要： Certain aspects of the present disclosure support a technique for updating the state of an artificial neuron. A first state of the artificial neuron can be first determined, wherein a neuron model for the artificial neuron has a closed-form solution in continuous time and wherein state dynamics of the neuron model are divided into two or more regimes. An operating regime for the artificial neuron can be determined based, at least in part, on the first state. The state of the artificial neuron can be updated based, at least in part, on the first state of the artificial neuron and the determined operating regime.
摘要翻译：本公开的某些方面支持用于更新人造神经元状态的技术。可以首先确定人造神经元的第一状态，其中用于人造神经元的神经元模型具有连续时间的闭合形式的解决方案，并且其中神经元模型的状态动力学被分为两个或多个方案。可以至少部分地基于第一状态来确定人造神经元的操作状态。可以至少部分地基于人造神经元的第一状态和确定的操作状态来更新人造神经元的状态。

5. 发明授权

US09275329B2 Behavioral homeostasis in artificial nervous systems using dynamical spiking neuron models 有权
标题翻译：使用动力学刺激神经元模型的人工神经系统中的行为体内平衡
公开(公告)号：US09275329B2
公开(公告)日：2016-03-01
申请号：US14167727
申请日：2014-01-29
申请人： QUALCOMM Incorporated
发明人： Jason Frank Hunzinger , Victor Hokkiu Chan
IPC分类号： G06F15/18 , G06N3/08 , G06N3/04
CPC分类号： G06N3/049
摘要： Methods and apparatus are provided for implementing behavioral homeostasis in artificial neurons that use a dynamical spiking neuron model. The homeostatic mechanism may be driven by neuron state, rather than by neuron spiking rate, and this mechanism may drive changes to the neuron temporal dynamics, rather than to contributions of input or weights. As a result, certain aspects of the present disclosure are a more natural fit with spiking neural networks and have many functional and computational advantages. One example method for implementing homeostasis of an artificial nervous system generally includes determining one or more state variables of a neuron model used by an artificial neuron, based at least in part on dynamics of the neuron model; determining one or more conditions based at least in part on the state variables; and adjusting the dynamics based at least in part on the conditions.
摘要翻译：提供了用于在使用动力学刺激神经元模型的人造神经元中实现行为动态平衡的方法和装置。稳态机制可以由神经元状态驱动，而不是由神经元峰值速率驱动，并且这种机制可以驱动神经元时间动力学的变化，而不是输入或权重的贡献。结果，本公开的某些方面与掺加神经网络更为自然，并且具有许多功能和计算的优点。用于实现人造神经系统的体内平衡的一个示例性方法通常包括至少部分地基于神经元模型的动力学来确定由人造神经元使用的神经元模型的一个或多个状态变量; 至少部分地基于状态变量确定一个或多个条件; 并且至少部分地基于条件来调整动力学。

6. 发明申请

US20140143193A1 METHOD AND APPARATUS FOR DESIGNING EMERGENT MULTI-LAYER SPIKING NETWORKS 审中-公开
标题翻译：用于设计紧急多层次扫描网络的方法和装置
公开(公告)号：US20140143193A1
公开(公告)日：2014-05-22
申请号：US13804299
申请日：2013-03-14
申请人： QUALCOMM INCORPORATED
发明人： Thomas Zheng , Jason Frank Hunzinger
IPC分类号： G06N3/08
CPC分类号： G06N3/049
摘要： Certain aspects of the present disclosure support a technique for designing an emergent multi-layer spiking neural network. Parameters of the neural network can be first determined based upon desired one or more functional features of the neural network. Then, the one or more functional features can be developed towards the desired functional features as the determined parameters are further adapted, tuned and updated. The parameters can comprise at least one of time constants of neuron circuits of the neural network, time constants of synapse connections of the neural network, timing parameters of the neural network, or timing aspects of learning in the neural network. The one or more functional features can comprise at least one of feature detection in a layer of the multi-layer spiking neural network or saliency detection in another layer of the multi-layer spiking neural network.
摘要翻译：本公开的某些方面支持用于设计紧急多层加标神经网络的技术。神经网络的参数可以首先基于神经网络的期望的一个或多个功能特征来确定。然后，随着所确定的参数被进一步调整，调整和更新，可以朝着期望的功能特征开发一个或多个功能特征。参数可以包括神经网络的神经元电路的时间常数，神经网络的突触连接的时间常数，神经网络的定时参数或神经网络中的学习的定时方面中的至少一个。一个或多个功能特征可以包括多层加标神经网络的层中的特征检测中的至少一个或多层加标神经网络的另一层中的显着性检测。

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