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

US09015092B2 Dynamically reconfigurable stochastic learning apparatus and methods 有权
标题翻译：动态可重构随机学习设备和方法
公开(公告)号：US09015092B2
公开(公告)日：2015-04-21
申请号：US13487576
申请日：2012-06-04
申请人： Oleg Sinyavskiy , Vadim Polonichko
发明人： Oleg Sinyavskiy , Vadim Polonichko
IPC分类号： G06N3/08 , G06N99/00
CPC分类号： G06N3/08 , G06N99/005
摘要： Generalized learning rules may be implemented. A framework may be used to enable adaptive signal processing system to flexibly combine different learning rules (supervised, unsupervised, reinforcement learning) with different methods (online or batch learning). The generalized learning framework may employ average performance function as the learning measure thereby enabling modular architecture where learning tasks are separated from control tasks, so that changes in one of the modules do not necessitate changes within the other. Separation of learning tasks from the control tasks implementations may allow dynamic reconfiguration of the learning block in response to a task change or learning method change in real time. The generalized learning apparatus may be capable of implementing several learning rules concurrently based on the desired control application and without requiring users to explicitly identify the required learning rule composition for that application.
摘要翻译：可以实施广义学习规则。可以使用框架来实现自适应信号处理系统以不同的方法（在线或批量学习）灵活地组合不同的学习规则（受监督，无监督，强化学习）。广义学习框架可以采用平均性能函数作为学习措施，从而使学习任务与控制任务分离的模块化架构，使得一个模块中的改变不需要在另一个模块内进行改变。将学习任务与控制任务实现分离可以允许响应于实时的任务改变或学习方法改变来学习块的动态重新配置。广义学习装置可能能够基于期望的控制应用同时实现若干学习规则，并且不需要用户明确地标识该应用所需的学习规则组合。

2. 发明授权

US07523658B1 Method for measuring river discharge in the presence of moving bottom 有权
标题翻译：在底部存在下测量河流排放的方法
公开(公告)号：US07523658B1
公开(公告)日：2009-04-28
申请号：US11956472
申请日：2007-12-14
申请人： Vadim Polonichko , Ramon Cabrera , John Sloat , Matthew J. Hull , Arthur R. Schmidt
发明人： Vadim Polonichko , Ramon Cabrera , John Sloat , Matthew J. Hull , Arthur R. Schmidt
IPC分类号： G01F13/00
CPC分类号： G01F1/002 , G01C13/00 , G01P5/18
摘要： A method for measuring channel flow discharge comprising the steps of: locating a platform carrying a fluid flow measurement device at a plurality of stations at spaced locations across a channel; determining the velocity of the platform at each station by averaging the differences between the position of the platform at a first time (t) and the position of the platform at a second time equal to the first time plus a position averaging interval (PI) for a plurality of different first times; obtaining current flow vs. depth profiles at each station by adjusting current velocity as measured by the current flow measuring device for the platform velocity; determining the flow discharge at each station.
摘要翻译：一种用于测量通道流量放电的方法，包括以下步骤：在穿过通道的间隔位置的多个站处定位承载流体流量测量装置的平台; 通过平均在第一时间（t）的平台的位置与在第一时间等于第一时间的平台的位置加上位置平均间隔（PI）之间的差异来确定每个站点处的平台的速度，以便多个不同的第一次; 通过调整由当前流量测量装置测量的平台速度的当前速度，在每个站点获得电流与深度分布; 确定每个站的流量排放。

3. 发明授权

US09256823B2 Apparatus and methods for efficient updates in spiking neuron network 有权
标题翻译：尖峰神经元网络有效更新的装置和方法
公开(公告)号：US09256823B2
公开(公告)日：2016-02-09
申请号：US13560891
申请日：2012-07-27
申请人： Oleg Sinyavskiy , Vadim Polonichko , Eugene Izhikevich , Jeffrey Alexander Levin
发明人： Oleg Sinyavskiy , Vadim Polonichko , Eugene Izhikevich , Jeffrey Alexander Levin
IPC分类号： G06N5/00 , G06F1/00 , G06N3/04
CPC分类号： G06N3/049
摘要： Efficient updates of connections in artificial neuron networks may be implemented. A framework may be used to describe the connections using a linear synaptic dynamic process, characterized by stable equilibrium. The state of neurons and synapses within the network may be updated, based on inputs and outputs to/from neurons. In some implementations, the updates may be implemented at regular time intervals. In one or more implementations, the updates may be implemented on-demand, based on the network activity (e.g., neuron output and/or input) so as to further reduce computational load associated with the synaptic updates. The connection updates may be decomposed into multiple event-dependent connection change components that may be used to describe connection plasticity change due to neuron input. Using event-dependent connection change components, connection updates may be executed on per neuron basis, as opposed to per-connection basis.
摘要翻译：可以实现人造神经网络中的连接的有效更新。可以使用框架来描述使用线性突触动态过程的连接，其特征在于稳定的平衡。可以基于对神经元的输入和输出来更新网络内的神经元和突触的状态。在一些实现中，可以以规则的时间间隔来实现更新。在一个或多个实现中，可以基于网络活动（例如，神经元输出和/或输入）按需实现更新，以便进一步减少与突触更新相关联的计算负荷。连接更新可以被分解成多个依赖于事件的连接变化组件，这些组件可用于描述由神经元输入引起的连接塑性变化。使用与事件相关的连接更改组件，可以基于每个神经元执行连接更新，而不是基于每个连接。

4. 发明申请

US20140032458A1 APPARATUS AND METHODS FOR EFFICIENT UPDATES IN SPIKING NEURON NETWORK 有权
标题翻译： SPIKE神经网络中高效更新的设备和方法
公开(公告)号：US20140032458A1
公开(公告)日：2014-01-30
申请号：US13560891
申请日：2012-07-27
申请人： Oleg Sinyavskiy , Vadim Polonichko , Eugene Izhikevich
发明人： Oleg Sinyavskiy , Vadim Polonichko , Eugene Izhikevich
IPC分类号： G06F15/18
CPC分类号： G06N3/049
摘要： Efficient updates of connections in artificial neuron networks may be implemented. A framework may be used to describe the connections using a linear synaptic dynamic process, characterized by stable equilibrium. The state of neurons and synapses within the network may be updated, based on inputs and outputs to/from neurons. In some implementations, the updates may be implemented at regular time intervals. In one or more implementations, the updates may be implemented on-demand, based on the network activity (e.g., neuron output and/or input) so as to further reduce computational load associated with the synaptic updates. The connection updates may be decomposed into multiple event-dependent connection change components that may be used to describe connection plasticity change due to neuron input. Using event-dependent connection change components, connection updates may be executed on per neuron basis, as opposed to per-connection basis.
摘要翻译：可以实现人造神经网络中的连接的有效更新。可以使用框架来描述使用线性突触动态过程的连接，其特征在于稳定的平衡。可以基于对神经元的输入和输出来更新网络内的神经元和突触的状态。在一些实现中，可以以规则的时间间隔来实现更新。在一个或多个实现中，可以基于网络活动（例如，神经元输出和/或输入）按需实现更新，以便进一步减少与突触更新相关联的计算负荷。连接更新可以被分解成多个依赖于事件的连接变化组件，这些组件可用于描述由神经元输入引起的连接塑性变化。使用与事件相关的连接更改组件，可以基于每个神经元执行连接更新，而不是基于每个连接。

5. 发明申请

US20130325775A1 DYNAMICALLY RECONFIGURABLE STOCHASTIC LEARNING APPARATUS AND METHODS 有权
标题翻译：动态可重构学习设备和方法
公开(公告)号：US20130325775A1
公开(公告)日：2013-12-05
申请号：US13487576
申请日：2012-06-04
申请人： Oleg Sinyavskiy , Vadim Polonichko
发明人： Oleg Sinyavskiy , Vadim Polonichko
IPC分类号： G06N3/08
CPC分类号： G06N3/08 , G06N99/005
摘要： Generalized learning rules may be implemented. A framework may be used to enable adaptive signal processing system to flexibly combine different learning rules (supervised, unsupervised, reinforcement learning) with different methods (online or batch learning). The generalized learning framework may employ average performance function as the learning measure thereby enabling modular architecture where learning tasks are separated from control tasks, so that changes in one of the modules do not necessitate changes within the other. Separation of learning tasks from the control tasks implementations may allow dynamic reconfiguration of the learning block in response to a task change or learning method change in real time. The generalized learning apparatus may be capable of implementing several learning rules concurrently based on the desired control application and without requiring users to explicitly identify the required learning rule composition for that application.
摘要翻译：可以实施广义学习规则。可以使用框架来实现自适应信号处理系统以不同的方法（在线或批量学习）灵活地组合不同的学习规则（受监督，无监督，强化学习）。广义学习框架可以采用平均性能函数作为学习措施，从而使学习任务与控制任务分离的模块化架构，使得一个模块中的改变不需要在另一个模块内进行改变。将学习任务与控制任务实现分离可以允许响应于实时的任务改变或学习方法改变来学习块的动态重新配置。广义学习装置可能能够基于期望的控制应用同时实现若干学习规则，并且不需要用户明确地标识该应用所需的学习规则组合。

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