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. 发明申请

WO2013106074A1 SENSORY INPUT PROCESSING APPARATUS AND METHODS 审中-公开
标题翻译：传感器输入处理装置及方法
公开(公告)号：WO2013106074A1
公开(公告)日：2013-07-18
申请号：PCT/US2012/040576
申请日：2012-06-01
申请人： BRAIN CORPORATION , PETRE, Csaba , SOKOL, Sach, Hansen , PIEKNIEWSKI, Filip, Lukasz , SZATMARY, Botond , IZHIKEVICH, Eugene, M.
发明人： PETRE, Csaba , SOKOL, Sach, Hansen , PIEKNIEWSKI, Filip, Lukasz , SZATMARY, Botond , IZHIKEVICH, Eugene, M.
IPC分类号： H05K1/00
CPC分类号： G06K9/6232 , G06K9/4628 , G06N3/049
摘要： Sensory input processing apparatus and methods useful for adaptive encoding and decoding of features. In one embodiment, the apparatus receives an input frame having a representation of the object feature, generates a sequence of sub-frames that are displaced from one another (and correspond to different areas within the frame), and encodes the sub-frame sequence into groups of pulses. The patterns of pulses are directed via transmission channels to detection apparatus configured to generate an output pulse upon detecting a predetermined pattern within received groups of pulses that is associated with the feature. Upon detecting a particular pattern, the detection apparatus provides feedback to the displacement module in order to optimize sub-frame displacement for detecting the feature of interest. In another embodiment, the detections apparatus elevates its sensitivity (and/or channel characteristics) to that particular pulse pattern when processing subsequent pulse group inputs, thereby increasing the likelihood of feature detection.
摘要翻译：感觉输入处理装置和方法对于特征的自适应编码和解码是有用的。在一个实施例中，设备接收具有对象特征的表示的输入帧，产生彼此相移（并对应于帧内的不同区域）的子帧序列，并将子帧序列编码成一组脉冲脉冲的模式经由传输通道引导到检测装置，该检测装置被配置为在检测到与特征相关联的所接收的脉冲组内的预定模式时产生输出脉冲。在检测到特定模式时，检测装置向位移模块提供反馈以优化用于检测感兴趣特征的子帧位移。在另一个实施例中，当处理后续的脉冲组输入时，检测装置将其灵敏度（和/或通道特性）提升到该特定脉冲模式，从而增加特征检测的可能性。

2. 发明申请

WO2013043903A1 APPARATUS AND METHODS FOR SYNAPTIC UPDATE IN A PULSE-CODED NETWORK 审中-公开
标题翻译：用于脉冲编码网络中的快速更新的装置和方法
公开(公告)号：WO2013043903A1
公开(公告)日：2013-03-28
申请号：PCT/US2012/056389
申请日：2012-09-20
申请人： BRAIN CORPORATION , IZHIKEVICH, Eugene, M. , PIEKNIEWSKI, Filip , NAGESWARAN, Jayram, Moorkanikara
发明人： IZHIKEVICH, Eugene, M. , PIEKNIEWSKI, Filip , NAGESWARAN, Jayram, Moorkanikara
IPC分类号： G06F15/18
CPC分类号： G06N3/049
摘要： Apparatus and methods for efficient synaptic update in a network such as a spiking neural network. In one embodiment, the post-synaptic updates, in response to generation of a post-synaptic pulse by a post-synaptic unit, are delayed until a subsequent pre-synaptic pulse is received by the unit. Pre-synaptic updates are performed first following by the post-synaptic update, thus ensuring synaptic connection status is up-to-date. The delay update mechanism is used in conjunction with system "flush7" events in order to ensure accurate network operation, and prevent loss of information under a variety of pre-synaptic and post-synaptic unit firing rates. A large network partition mechanism is used in one variant with network processing apparatus in order to enable processing of network signals in a limited functionality embedded hardware environment.
摘要翻译：用于在诸如尖峰神经网络的网络中有效突触更新的装置和方法。在一个实施例中，响应于由突触后单元产生后突触脉冲的突触后更新被延迟，直到该单元接收到后续的突触前脉冲。突触前更新先由突触后更新执行，从而确保突触连接状态是最新的。延迟更新机制与系统“flush7”事件结合使用，以确保准确的网络运行，并防止在各种突触前和突触后单位点火速率下的信息丢失。在网络处理装置的一个变型中使用大的网络分区机制，以便能够在有限的功能嵌入式硬件环境中处理网络信号。

3. 发明申请

WO2013043610A1 ELEMENTARY NETWORK DESCRIPTION FOR NEUROMORPHIC SYSTEMS 审中-公开
标题翻译：神经系统的基本网络描述
公开(公告)号：WO2013043610A1
公开(公告)日：2013-03-28
申请号：PCT/US2012/055933
申请日：2012-09-18
申请人： BRAIN CORPORATION , IZHIKEVICH, Eugene M. , SZATMARY, Botond , PETRE, Csaba , NAGESWARAN, Jayram Moorkanikara , PIEKNIEWSKI, Filip
发明人： IZHIKEVICH, Eugene M. , SZATMARY, Botond , PETRE, Csaba , NAGESWARAN, Jayram Moorkanikara , PIEKNIEWSKI, Filip
IPC分类号： G06F15/18
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。

4. 发明申请

WO2012167164A1 APPARATUS AND METHODS FOR TEMPORALLY PROXIMATE OBJECT RECOGNITION 审中-公开
标题翻译：用于临时遗传对象识别的装置和方法
公开(公告)号：WO2012167164A1
公开(公告)日：2012-12-06
申请号：PCT/US2012/040567
申请日：2012-06-01
申请人： BRAIN CORPORATION , PIEKNIEWSKI, Filip, Lukasz , PETRE, Csaba , SOKOL, Sach, Hansen , SZATMARY, Botond , NAGESWARAN, Jayram, Moorkanikara , IZHIKEVICH, Eugene, M.
发明人： PIEKNIEWSKI, Filip, Lukasz , PETRE, Csaba , SOKOL, Sach, Hansen , SZATMARY, Botond , NAGESWARAN, Jayram, Moorkanikara , IZHIKEVICH, Eugene, M.
IPC分类号： G06K9/00
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的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。

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