专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

91. 发明申请

US20140019393A1 UNIVERSAL, ONLINE LEARNING IN MULTI-MODAL PERCEPTION-ACTION SEMILATTICES 有权
标题翻译：通用，在线学习多模式感知行为半身像
公开(公告)号：US20140019393A1
公开(公告)日：2014-01-16
申请号：US13325316
申请日：2011-12-14
申请人： Dharmendra S. Modha
发明人： Dharmendra S. Modha
IPC分类号： G06N3/04
CPC分类号： G06N3/04 , G06N3/049 , G06N3/10
摘要： In one embodiment, the present invention provides a method for interconnecting neurons in a neural network. At least one node among a first set of nodes is interconnected to at least one node among a second set of nodes, and nodes of the first and second set are arranged in a lattice. At least one node of the first set represents a sensory-motor modality of the neural network. At least one node of the second set is a union of at least two nodes of the first set. Each node in the lattice has an acyclic digraph comprising multiple vertices and directed edges. Each vertex represents a neuron population. Each directed edge comprises multiple synaptic connections. Vertices in different acyclic digraphs are interconnected using an acyclic bottom-up digraph. The bottom-up digraph has a corresponding acyclic top-down digraph. Vertices in the bottom-up digraph are interconnected to vertices in the top-down digraph.
摘要翻译：在一个实施例中，本发明提供了一种用于在神经网络中互连神经元的方法。第一组节点中的至少一个节点被互连到第二组节点中的至少一个节点，并且第一组和第二组的节点被布置成格子。第一组的至少一个节点表示神经网络的感觉运动模态。第二组的至少一个节点是第一组的至少两个节点的并集。格子中的每个节点都具有包含多个顶点和有向边的非循环图。每个顶点代表一个神经元群体。每个定向边缘包括多个突触连接。不同非循环图中的顶点使用非循环的自下而上的有向图相互连接。自下而上的有向图具有相应的非循环自顶向下的有向图。自下而上的图中的顶点与自顶向下的图中的顶点相互连接。

92. 发明申请

US20130073494A1 EVENT-DRIVEN UNIVERSAL NEURAL NETWORK CIRCUIT 有权
公开(公告)号：US20130073494A1
公开(公告)日：2013-03-21
申请号：US13235343
申请日：2011-09-16
申请人： Dharmendra S. Modha
发明人： Dharmendra S. Modha
IPC分类号： G06N3/04 , G06N3/08
CPC分类号： G06N3/08 , G06N3/04 , G06N3/049 , G06N3/063
摘要： The present invention provides an event-driven universal neural network circuit. The circuit comprises a plurality of neural modules. Each neural module comprises multiple digital neurons such that each neuron in a neural module has a corresponding neuron in another neural module. An interconnection network comprising a plurality of digital synapses interconnects the neural modules. Each synapse interconnects a first neural module to a second neural module by interconnecting a neuron in the first neural module to a corresponding neuron in the second neural module. Corresponding neurons in the first neural module and the second neural module communicate via the synapses. Each synapse comprises a learning rule associating a neuron in the first neural module with a corresponding neuron in the second neural module. A control module generates signals which define a set of time steps for event-driven operation of the neurons and event communication via the interconnection network.

93. 发明申请

US20130073493A1 UNSUPERVISED, SUPERVISED, AND REINFORCED LEARNING VIA SPIKING COMPUTATION 有权
公开(公告)号：US20130073493A1
公开(公告)日：2013-03-21
申请号：US13235342
申请日：2011-09-16
申请人： Dharmendra S. Modha
发明人： Dharmendra S. Modha
IPC分类号： G06N3/04 , G06N3/08
CPC分类号： G06N3/08 , G06N3/04 , G06N3/049 , G06N3/063 , G06N3/088
摘要： The present invention relates to unsupervised, supervised and reinforced learning via spiking computation. The neural network comprises a plurality of neural modules. Each neural module comprises multiple digital neurons such that each neuron in a neural module has a corresponding neuron in another neural module. An interconnection network comprising a plurality of edges interconnects the plurality of neural modules. Each edge interconnects a first neural module to a second neural module, and each edge comprises a weighted synaptic connection between every neuron in the first neural module and a corresponding neuron in the second neural module.

94. 发明申请

US20120109864A1 NEUROMORPHIC AND SYNAPTRONIC SPIKING NEURAL NETWORK WITH SYNAPTIC WEIGHTS LEARNED USING SIMULATION 有权
标题翻译：神经网络和同步扫描神经网络与使用模拟学习的应激权重
公开(公告)号：US20120109864A1
公开(公告)日：2012-05-03
申请号：US12916332
申请日：2010-10-29
申请人： Dharmendra S. Modha
发明人： Dharmendra S. Modha
IPC分类号： G06N3/08
CPC分类号： G06N3/08 , G06N3/04 , G06N3/049 , G06N3/063
摘要： Embodiments of the invention provide neuromorphic-synaptronic systems, including neuromorphic-synaptronic circuits implementing spiking neural network with synaptic weights learned using simulation. One embodiment includes simulating a spiking neural network to generate synaptic weights learned via the simulation while maintaining one-to-one correspondence between the simulation and a digital circuit chip. The learned synaptic weights are loaded into the digital circuit chip implementing a spiking neural network, the digital circuit chip comprising a neuromorphic-synaptronic spiking neural network including plural synapse devices interconnecting multiple digital neurons.
摘要翻译：本发明的实施方案提供神经形态 - synaptronic系统，其包括使用模拟学习的具有突触重量的尖峰神经网络的神经形态 - synaptronic电路。一个实施例包括模拟加标神经网络以产生通过模拟学习的突触权重，同时保持模拟和数字电路芯片之间的一对一对应关系。所学的突触权重被加载到实现尖峰神经网络的数字电路芯片中，该数字电路芯片包括一个包含多个连接多个数字神经元的突触装置的神经 - 突触间期刺激神经网络。

95. 发明申请

US20110182349A1 ADAPTIVE AND INTEGRATED VISUALIZATION OF SPATIOTEMPORAL DATA FROM LARGE-SCALE SIMULATIONS 失效
标题翻译：大规模模拟的空间数据的自适应和集成可视化
公开(公告)号：US20110182349A1
公开(公告)日：2011-07-28
申请号：US12695119
申请日：2010-01-27
申请人： Rajagopal Ananthanarayanan , Shyamal S. Chandra , Dharmendra S. Modha , Raghavendra Singh
发明人： Rajagopal Ananthanarayanan , Shyamal S. Chandra , Dharmendra S. Modha , Raghavendra Singh
IPC分类号： H04N11/04 , G06T15/00
CPC分类号： G11B27/10 , G06N3/049 , G06T11/206 , G11B27/34
摘要： Adaptive and integrated visualization of spatiotemporal data from large-scale simulation, is provided. A simulation is performed utilizing a simulator comprising multiple processors, generating spatiotemporal data samples from the simulation. Each data sample has spatial coordinates with a time stamp at a specific time resolution, and a tag. The data samples are assembled into data streams based on at least one of a spatial relationship and the corresponding tag. Each data stream is encoded into multiple formats, and an integrated and adaptive visualization of the data streams is displayed, wherein various data streams are simultaneously and synchronously displayed.
摘要翻译：提供了大规模模拟的时空数据的自适应和综合可视化。使用包括多个处理器的模拟器执行模拟，从仿真生成时空数据样本。每个数据样本具有具有特定时间分辨率的时间戳的空间坐标和标签。基于空间关系和相应标签中的至少一个将数据样本组装成数据流。每个数据流被编码成多种格式，并且显示数据流的集成和自适应可视化，其中同时和同步地显示各种数据流。

96. 发明授权

US07395377B2 Method and system for adaptive back-off and advance for non-volatile storage (NVS) occupancy level management 有权
标题翻译：用于非易失性存储（NVS）占用级别管理的自适应退避和提前的方法和系统
公开(公告)号：US07395377B2
公开(公告)日：2008-07-01
申请号：US11407797
申请日：2006-04-20
申请人： Binny S. Gill , Dharmendra S. Modha
发明人： Binny S. Gill , Dharmendra S. Modha
IPC分类号： G06F12/00
CPC分类号： G06F12/0804 , G06F12/0866 , G06F2212/222
摘要： A technique for determining when to destage write data from a fast, NVS of a computer system from an upper level to a lower level of storage in the computer system comprises adaptively varying a destage rate of the NVS according to a current storage occupancy of the NVS; maintaining a high threshold level for the NVS; maintaining a low threshold level that is set to be a predetermined fixed amount below the high threshold; setting the destage rate of the NVS to zero when the NVS occupancy is below the low threshold; setting the destage rate of the NVS to be maximum when the NVS occupancy is above the high threshold; linearly increasing the destage rate of the NVS from zero to maximum as the NVS occupancy goes from the low to the high threshold; and adaptively varying the high threshold in response to a dynamic computer storage workload.
摘要翻译：一种用于确定何时从计算机系统的快速NVS将计算机系统的写入数据从计算机系统中的较高级别存储到较低级别的存储装置的技术包括根据NVS的当前存储占用自适应地改变NVS的流率 ; 维持NVS的高门槛值; 保持低阈值水平，其被设置为低于高阈值的预定固定量; 当NVS占用率低于低阈值时，将NVS的流出率设置为零; 当NVS占用率高于高阈值时，将NVS的流出率设置为最大值; 随着NVS占用率从低到高的阈值，将NVS的流失率从零线性上升到最大值; 以及响应于动态计算机存储工作负载自适应地改变高阈值。

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