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

US09122994B2 Apparatus and methods for temporally proximate object recognition 有权
标题翻译：用于时间上靠近物体识别的装置和方法
公开(公告)号：US09122994B2
公开(公告)日：2015-09-01
申请号：US13152105
申请日：2011-06-02
申请人： Filip Lukasz Piekniewski , Csaba Petre , Sach Hansen Sokol , Botond Szatmary , Jayram Moorkanikara Nageswaran , Eugene M. Izhikevich
发明人： Filip Lukasz Piekniewski , Csaba Petre , Sach Hansen Sokol , Botond Szatmary , Jayram Moorkanikara Nageswaran , Eugene M. Izhikevich
IPC分类号： G06N3/04
CPC分类号： G06N3/049
摘要： Object recognition apparatus and methods useful for extracting information from an input signal. In one embodiment, the input signal is representative of an element of an image, and the extracted information is encoded into patterns of pulses. The patterns of pulses are directed via transmission channels to a plurality of detector nodes configured to generate an output pulse upon detecting an object of interest. Upon detecting a particular object, a given detector node elevates its sensitivity to that particular object when processing subsequent inputs. In one implementation, one or more of the detector nodes are also configured to prevent adjacent detector nodes from generating detection signals in response to the same object representation. The object recognition apparatus modulates properties of the transmission channels by promoting contributions from channels carrying information used in object recognition.
摘要翻译：用于从输入信号中提取信息的对象识别装置和方法。在一个实施例中，输入信号表示图像的元素，并且将所提取的信息编码为脉冲图案。脉冲的模式经由传输通道被引导到多个检测器节点，其被配置为在检测到感兴趣对象时产生输出脉冲。当检测到特定物体时，给定的检测器节点在处理后续输入时提高其对该特定物体的敏感度。在一个实现中，一个或多个检测器节点还被配置为防止相邻检测器节点响应于相同的对象表示而产生检测信号。对象识别装置通过促进携带在对象识别中使用的信息的信道的贡献来调制传输信道的属性。

2. 发明申请

US20130325766A1 SPIKING NEURON NETWORK APPARATUS AND METHODS 审中-公开
标题翻译： SPIKE神经网络设备和方法
公开(公告)号：US20130325766A1
公开(公告)日：2013-12-05
申请号：US13488114
申请日：2012-06-04
申请人： CSABA PETRE , BOTOND SZATMARY
发明人： CSABA PETRE , BOTOND SZATMARY
IPC分类号： G06N3/02
CPC分类号： G06N3/049
摘要： Apparatus and methods for heterosynaptic plasticity in a spiking neural network having multiple neurons configured to process sensory input. In one exemplary approach, a heterosynaptic plasticity mechanism is configured to select alternate plasticity rules when performing neuronal updates. The selection mechanism is adapted based on recent post-synaptic activity of neighboring neurons. When neighbor activity is low, a regular STDP update rule is effectuated. When neighbor activity is high, an alternate STDP update rule, configured to reduce probability of post-synaptic spike generation by the neuron associated with the update, is used. The heterosynaptic mechanism impedes that neuron to respond to (or learn) features within the sensory input that have been detected by neighboring neurons, thereby forcing the neuron to learn a different feature or feature set. The heterosynaptic methodology advantageously introduces competition among neighboring neurons, in order to increase receptive field diversity and improve feature detection capabilities of the network.
摘要翻译：具有配置成处理感觉输入的多个神经元的加标神经网络中的异质突触可塑性的装置和方法。在一个示例性方法中，异构突变可塑性机制被配置为在执行神经元更新时选择替代可塑性规则。选择机制是根据近期邻近神经元的突触后活动进行调整的。当邻居活动较低时，会执行常规STDP更新规则。当邻居活动高时，使用替代STDP更新规则，配置为降低与更新相关联的神经元产生突触后尖峰的概率。异常突触机制阻碍神经元响应（或学习）由相邻神经元检测到的感觉输入内的（或学习）特征，从而迫使神经元学习不同的特征或特征集。异质突变方法有利地引入相邻神经元之间的竞争，以便增加接收场分集并提高网络的特征检测能力。

3. 发明授权

US09224090B2 Sensory input processing apparatus in a spiking neural network 有权
标题翻译：感兴趣的输入处理装置在加标神经网络中
公开(公告)号：US09224090B2
公开(公告)日：2015-12-29
申请号：US13465903
申请日：2012-05-07
申请人： Filip Piekniewski , Eugene Izhikevich , Botond Szatmary , Csaba Petre
发明人： Filip Piekniewski , Eugene Izhikevich , Botond Szatmary , Csaba Petre
IPC分类号： G06N3/04
CPC分类号： G06N3/04 , G06N3/049 , G06N3/088
摘要： Apparatus and methods for feedback in a spiking neural network. In one approach, spiking neurons receive sensory stimulus and context signal that correspond to the same context. When the stimulus provides sufficient excitation, neurons generate response. Context connections are adjusted according to inverse spike-timing dependent plasticity. When the context signal precedes the post synaptic spike, context synaptic connections are depressed. Conversely, whenever the context signal follows the post synaptic spike, the connections are potentiated. The inverse STDP connection adjustment ensures precise control of feedback-induced firing, eliminates runaway positive feedback loops, enables self-stabilizing network operation. In another aspect of the invention, the connection adjustment methodology facilitates robust context switching when processing visual information. When a context (such an object) becomes intermittently absent, prior context connection potentiation enables firing for a period of time. If the object remains absent, the connection becomes depressed thereby preventing further firing.
摘要翻译：用于在加标神经网络中反馈的装置和方法。在一种方法中，刺激神经元接收对应于相同上下文的感觉刺激和上下文信号。当刺激提供足够的激发时，神经元产生反应。上下文连接根据反时限相关的可塑性进行调整。当上下文信号在后突触尖端之前时，上下文突触连接被按下。相反，只要上下文信号跟随突触后的尖峰，连接就被加强了。反向STDP连接调整可确保对反馈引发的精确控制，消除失控的正反馈回路，实现自稳定网络运行。在本发明的另一方面，当处理视觉信息时，连接调整方法有助于鲁棒的上下文切换。当上下文（这样的对象）间歇地不存在时，先前的上下文连接增强使得能够触发一段时间。如果物体不存在，则连接被压下，从而防止进一步的烧制。

4. 发明授权

US08719199B2 Systems and methods for providing a neural network having an elementary network description for efficient implementation of event-triggered plasticity rules 失效
标题翻译：用于提供具有用于有效实现事件触发可塑性规则的基本网络描述的神经网络的系统和方法
公开(公告)号：US08719199B2
公开(公告)日：2014-05-06
申请号：US13239163
申请日：2011-09-21
申请人： Eugene M. Izhikevich , Botond Szatmary , Csaba Petre , Filip Piekniewski , Jayram Moorkanikara Nageswaran
发明人： Eugene M. Izhikevich , Botond Szatmary , Csaba Petre , Filip Piekniewski , Jayram Moorkanikara Nageswaran
IPC分类号： G05B13/02 , G06N3/08
CPC分类号： G06N3/08 , G05B13/027 , G06N3/049 , G06N3/10
摘要： A simple format is disclosed and referred to as Elementary Network Description (END). The format can fully describe a large-scale neuronal model and embodiments of software or hardware engines to simulate such a model efficiently. The architecture of such neuromorphic engines is optimal for high-performance parallel processing of spiking networks with spike-timing dependent plasticity. The software and hardware engines are optimized to take into account short-term and long-term synaptic plasticity in the form of LTD, LTP, and STDP.
摘要翻译：公开了一种简单的格式，并被称为基本网络描述（END）。该格式可以充分描述大规模神经元模型和软件或硬件引擎的实施例，以有效地模拟这种模型。这种神经形态发动机的架构对于具有尖峰时间依赖可塑性的加标网络的高性能并行处理是最佳的。软件和硬件引擎经过优化考虑了LTD，LTP和STDP形式的短期和长期突触可塑性。

5. 发明申请

US20130325777A1 SPIKING NEURON NETWORK APPARATUS AND METHODS 有权
公开(公告)号：US20130325777A1
公开(公告)日：2013-12-05
申请号：US13488106
申请日：2012-06-04
申请人： Csaba Petre , Botond Szatmary
发明人： Csaba Petre , Botond Szatmary
IPC分类号： G06N3/04
CPC分类号： G06N3/049 , G06N3/06 , G06N3/0635 , G06N3/088
摘要： Apparatus and methods for heterosynaptic plasticity in a spiking neural network having multiple neurons configured to process sensory input. In one exemplary approach, a heterosynaptic plasticity mechanism is configured to select alternate plasticity rules when performing neuronal updates. The selection mechanism is adapted based on recent post-synaptic activity of neighboring neurons. When neighbor activity is low, a regular STDP update rule is effectuated. When neighbor activity is high, an alternate STDP update rule, configured to reduce probability of post-synaptic spike generation by the neuron associated with the update, is used. The heterosynaptic mechanism impedes that neuron to respond to (or learn) features within the sensory input that have been detected by neighboring neurons, thereby forcing the neuron to learn a different feature or feature set. The heterosynaptic methodology advantageously introduces competition among neighboring neurons, in order to increase receptive field diversity and improve feature detection capabilities of the network.

6. 发明申请

US20130297539A1 SPIKING NEURAL NETWORK OBJECT RECOGNITION APPARATUS AND METHODS 审中-公开
标题翻译： SPIKING神经网络对象识别装置及方法
公开(公告)号：US20130297539A1
公开(公告)日：2013-11-07
申请号：US13465918
申请日：2012-05-07
申请人： Filip Piekniewski , Eugene Izhikevich , Botond Szatmary , Csaba Petre
发明人： Filip Piekniewski , Eugene Izhikevich , Botond Szatmary , Csaba Petre
IPC分类号： G06N3/02
CPC分类号： G06N3/049
摘要： Apparatus and methods for feedback in a spiking neural network. In one approach, spiking neurons receive sensory stimulus and context signal that correspond to the same context. When the stimulus provides sufficient excitation, neurons generate response. Context connections are adjusted according to inverse spike-timing dependent plasticity. When the context signal precedes the post synaptic spike, context synaptic connections are depressed. Conversely, whenever the context signal follows the post synaptic spike, the connections are potentiated. The inverse STDP connection adjustment ensures precise control of feedback-induced firing, eliminates runaway positive feedback loops, enables self-stabilizing network operation. In another aspect of the invention, the connection adjustment methodology facilitates robust context switching when processing visual information. When a context (such an object) becomes intermittently absent, prior context connection potentiation enables firing for a period of time. If the object remains absent, the connection becomes depressed thereby preventing further firing.
摘要翻译：用于在加标神经网络中反馈的装置和方法。在一种方法中，刺激神经元接收对应于相同上下文的感觉刺激和上下文信号。当刺激提供足够的激发时，神经元产生反应。上下文连接根据反时限相关的可塑性进行调整。当上下文信号在后突触尖端之前时，上下文突触连接被按下。相反，只要上下文信号跟随突触后的尖峰，连接就被加强了。反向STDP连接调整可确保对反馈引发的精确控制，消除失控的正反馈回路，实现自稳定网络运行。在本发明的另一方面，当处理视觉信息时，连接调整方法有助于鲁棒的上下文切换。当上下文（这样的对象）间歇地不存在时，先前的上下文连接增强使得能够触发一段时间。如果物体不存在，则连接被压下，从而防止进一步的烧制。

7. 发明申请

US20130251278A1 INVARIANT PULSE LATENCY CODING SYSTEMS AND METHODS 有权
标题翻译：不确定脉冲序列编码系统和方法
公开(公告)号：US20130251278A1
公开(公告)日：2013-09-26
申请号：US13895246
申请日：2013-05-15
申请人： Eugene M. Izhikevich , Botond Szatmary , Csaba Petre
发明人： Eugene M. Izhikevich , Botond Szatmary , Csaba Petre
IPC分类号： G06T9/00
CPC分类号： H04N19/107 , G06K9/46 , G06N3/049 , G06T7/20 , G06T7/40 , G06T9/002 , G06T2207/10016 , H04B14/026 , H04N19/00
摘要： Systems and methods for processing image signals are described. One method comprises obtaining a generator signal based on an image signal and determining relative latencies associated with two or more pulses in a pulsed signal using a function of the generator signal that can comprise a logarithmic function. The function of the generator signal can be the absolute value of its argument. Information can be encoded in the pattern of relative latencies. Latencies can be determined using a scaling parameter that is calculated from a history of the image signal. The pulsed signal is typically received from a plurality of channels and the scaling parameter corresponds to at least one of the channels. The scaling parameter may be adaptively calculated such that the latency of the next pulse falls within one or more of a desired interval and an optimal interval.
摘要翻译：描述用于处理图像信号的系统和方法。一种方法包括基于图像信号获得发生器信号，并且使用可以包括对数函数的发生器信号的函数来确定与脉冲信号中的两个或更多个脉冲相关联的相对延迟。发电机信号的功能可以是其参数的绝对值。信息可以以相对延迟的模式进行编码。可以使用从图像信号的历史计算的缩放参数来确定延迟。通常从多个通道接收脉冲信号，并且缩放参数对应于至少一个通道。可以自适应地计算缩放参数，使得下一个脉冲的等待时间落入期望的间隔和最佳间隔的一个或多个之内。

8. 发明申请

US20130073484A1 ELEMENTARY NETWORK DESCRIPTION FOR EFFICIENT MEMORY MANAGEMENT IN NEUROMORPHIC SYSTEMS 失效
标题翻译：神经网络系统中有效的内存管理的基本网络描述
公开(公告)号：US20130073484A1
公开(公告)日：2013-03-21
申请号：US13239155
申请日：2011-09-21
申请人： Eugene M. Izhikevich , Botond Szatmary , Csaba Petre , Filip Piekniewski
发明人： Eugene M. Izhikevich , Botond Szatmary , Csaba Petre , Filip Piekniewski
IPC分类号： G06N3/04
CPC分类号： G06N3/10 , G06N3/04 , G06N3/049
摘要： A simple format is disclosed and referred to as Elementary Network Description (END). The format can fully describe a large-scale neuronal model and embodiments of software or hardware engines to simulate such a model efficiently. The architecture of such neuromorphic engines is optimal for high-performance parallel processing of spiking networks with spike-timing dependent plasticity. Methods for managing memory in a processing system are described whereby memory can be allocated among a plurality of elements and rules configured for each element such that the parallel execution of the spiking networks is most optimal.
摘要翻译：公开了一种简单的格式，并被称为基本网络描述（END）。该格式可以充分描述大规模神经元模型和软件或硬件引擎的实施例，以有效地模拟这种模型。这种神经形态发动机的架构对于具有尖峰时间依赖可塑性的加标网络的高性能并行处理是最佳的。描述了用于管理处理系统中的存储器的方法，其中可以在为每个元件配置的多个元件和规则之间分配存储器，使得加标网络的并行执行是最佳的。

9. 发明申请

US20070100780A1 Hybrid control device 有权
标题翻译：混合控制装置
公开(公告)号：US20070100780A1
公开(公告)日：2007-05-03
申请号：US11530685
申请日：2006-09-11
申请人： Jason Fleischer , Botond Szatmary , Donald Hutson , Douglas Moore , James Snook , Gerald Edelman , Jeffrey Krichmar
发明人： Jason Fleischer , Botond Szatmary , Donald Hutson , Douglas Moore , James Snook , Gerald Edelman , Jeffrey Krichmar
IPC分类号： G06N3/02
CPC分类号： G06N3/0427 , G05B13/027 , G05B15/02 , G05B2219/39292 , G05B2219/39385 , G06K9/00664
摘要： A hybrid control system for a robot can include a neuronal control portion and a non-neuronal control portion.
摘要翻译：用于机器人的混合控制系统可以包括神经元控制部分和非神经元控制部分。

10. 发明授权

US09104973B2 Elementary network description for neuromorphic systems with plurality of doublets wherein doublet events rules are executed in parallel 有权
标题翻译：具有多个双重的神经形态系统的基本网络描述，其中并行执行双重事件规则
公开(公告)号：US09104973B2
公开(公告)日：2015-08-11
申请号：US13239123
申请日：2011-09-21
申请人： Eugene M. Izhikevich , Botond Szatmary , Csaba Petre , Jayram Moorkanikara Nageswaran , Filip Piekniewski
发明人： Eugene M. Izhikevich , Botond Szatmary , Csaba Petre , Jayram Moorkanikara Nageswaran , Filip Piekniewski
IPC分类号： G06N3/04 , G06N3/063 , G06N99/00
CPC分类号： G06N3/049 , G06N3/0454 , G06N3/063 , G06N99/007
摘要： A simple format is disclosed and referred to as Elementary Network Description (END). The format can fully describe a large-scale neuronal model and embodiments of software or hardware engines to simulate such a model efficiently. The architecture of such neuromorphic engines is optimal for high-performance parallel processing of spiking networks with spike-timing dependent plasticity. Neuronal network and methods for operating neuronal networks comprise a plurality of units, where each unit has a memory and a plurality of doublets, each doublet being connected to a pair of the plurality of units. Execution of unit update rules for the plurality of units is order-independent and execution of doublet event rules for the plurality of doublets is order-independent.
摘要翻译：公开了一种简单的格式，并被称为基本网络描述（END）。该格式可以充分描述大规模神经元模型和软件或硬件引擎的实施例，以有效地模拟这种模型。这种神经形态发动机的架构对于具有尖峰时间依赖可塑性的加标网络的高性能并行处理是最佳的。用于操作神经元网络的神经元网络和方法包括多个单元，其中每个单元具有存储器和多个双重元件，每个双引脚连接到一对多个单元。多个单元的单元更新规则的执行是与订单无关的，并且用于多个双工的双重事件规则的执行是与订单无关的。

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