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

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。

2. 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。

3. 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。

4. 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。

5. 发明授权

US09460387B2 Apparatus and methods for implementing event-based updates in neuron networks 有权
标题翻译：用于在神经元网络中实现基于事件的更新的装置和方法
公开(公告)号：US09460387B2
公开(公告)日：2016-10-04
申请号：US13588774
申请日：2012-08-17
申请人： Oleg Sinyavskiy , Eugene Izhikevich
发明人： Oleg Sinyavskiy , Eugene Izhikevich
IPC分类号： G06N3/10 , G06N3/04
CPC分类号： G06N3/10 , G06N3/049
摘要： Event-based updates in artificial neuron networks may be implemented. An internal event may be defined in order to update incoming connections of a neuron. The internal event may be triggered by an external signal and/or internally by the neuron. A reinforcement signal may be used to trigger an internal event of a neuron in order to perform synaptic updates without necessitating post-synaptic response. An external event may be defined in order to deliver response of the neuron to desired targets. The external and internal events may be combined into a composite event configured to effectuate connection update and spike delivery to post-synaptic target. The scope of the internal event may comprise the respective neuron and does not extend to other neurons of the network. Conversely, the scope of the external event may extend to other neurons of the network via, for example, post-synaptic spike delivery.
摘要翻译：可以实现人造神经网络中基于事件的更新。可以定义内部事件以便更新神经元的传入连接。内部事件可能由外部信号和/或内部由神经元触发。加强信号可以用于触发神经元的内部事件，以便执行突触更新，而不需要突触后响应。可以定义外部事件以便将神经元的响应递送到期望的目标。外部和内部事件可以组合成组合事件，配置为实现连接更新和尖峰传递到突触后目标。内部事件的范围可以包括相应的神经元，并且不延伸到网络的其他神经元。相反，外部事件的范围可以通过例如突触后尖峰传递来延伸到网络的其他神经元。

6. 发明申请

US20140277718A1 ADAPTIVE PREDICTOR APPARATUS AND METHODS 有权
标题翻译：自适应预测装置和方法
公开(公告)号：US20140277718A1
公开(公告)日：2014-09-18
申请号：US13842530
申请日：2013-03-15
申请人： Eugene Izhikevich , Oleg Sinyavskiy , Jean-Baptiste Passot
发明人： Eugene Izhikevich , Oleg Sinyavskiy , Jean-Baptiste Passot
IPC分类号： B25J9/16
CPC分类号： B25J9/163 , B25J9/161 , G05B2219/39292 , G05B2219/39298 , G05B2219/40499 , G06N3/008 , G06N3/049
摘要： Apparatus and methods for training and operating of robotic devices. Robotic controller may comprise a predictor apparatus configured to generate motor control output. The predictor may be operable in accordance with a learning process based on a teaching signal comprising the control output. An adaptive controller block may provide control output that may be combined with the predicted control output. The predictor learning process may be configured to learn the combined control signal. Predictor training may comprise a plurality of trials. During initial trial, the control output may be capable of causing a robot to perform a task. During intermediate trials, individual contributions from the controller block and the predictor may be inadequate for the task. Upon learning, the control knowledge may be transferred to the predictor so as to enable task execution in absence of subsequent inputs from the controller. Control output and/or predictor output may comprise multi-channel signals.
摘要翻译：机器人装置的训练和操作的装置和方法。机器人控制器可以包括被配置为产生电动机控制输出的预测器装置。预测器可以根据包括控制输出的教学信号的学习过程来操作。自适应控制器块可以提供可以与预测的控制输出组合的控制输出。预测器学习过程可以被配置为学习组合的控制信号。预测器训练可以包括多个试验。在初始试验期间，控制输出可能导致机器人执行任务。在中期试验期间，控制器块和预测器的个人贡献可能不足以完成任务。在学习时，控制知识可以被传送到预测器，以便在没有来自控制器的后续输入的情况下使得能够执行任务。控制输出和/或预测器输出可以包括多信道信号。

7. 发明申请

US20140317035A1 APPARATUS AND METHODS FOR EVENT-BASED COMMUNICATION IN A SPIKING NEURON NETWORKS 有权
标题翻译：一种用于基于事件的通信在神经网络中的装置和方法
公开(公告)号：US20140317035A1
公开(公告)日：2014-10-23
申请号：US13868944
申请日：2013-04-23
申请人： Botond Szatmary , Micah Richert , Oleg Sinyavskiy , Eugene Izhikevich
发明人： Botond Szatmary , Micah Richert , Oleg Sinyavskiy , Eugene Izhikevich
IPC分类号： G06N3/04
CPC分类号： G06N3/049
摘要： Apparatus and methods for event based communication in a spiking neuron network. The network may comprise units communicating by spikes via synapses. The spikes may communicate a payload data. The data may comprise one or more bits. The payload may be stored in a buffer of a pre-synaptic unit and be configured to accessed by the post-synaptic unit. Spikes of different payload may cause different actions by the recipient unit. Sensory input spikes may cause postsynaptic response and trigger connection efficacy update. Teaching input spikes trigger the efficacy update without causing the post-synaptic response.
摘要翻译：用于加速神经元网络中基于事件的通信的装置和方法。网络可以包括通过突触通过尖峰通信的单元。峰值可以传送有效载荷数据。数据可以包括一个或多个位。有效载荷可以存储在突触前单元的缓冲器中，并且被配置为由突触后单元访问。不同有效负载的峰值可能导致接收单元的不同动作。感觉输入尖峰可能会引起突触后反应并触发连接功效更新。教学输入尖峰触发功效更新，而不会导致突触后反应。

8. 发明申请

US20140052679A1 APPARATUS AND METHODS FOR IMPLEMENTING EVENT-BASED UPDATES IN SPIKING NEURON NETWORKS 有权
标题翻译：在神经网络中实现基于事件的更新的装置和方法
公开(公告)号：US20140052679A1
公开(公告)日：2014-02-20
申请号：US13588774
申请日：2012-08-17
申请人： Oleg Sinyavskiy , Eugene Izhikevich
发明人： Oleg Sinyavskiy , Eugene Izhikevich
IPC分类号： G06N3/10 , G06N3/08
CPC分类号： G06N3/10 , G06N3/049
摘要： Event-based updates in artificial neuron networks may be implemented. An internal event may be defined in order to update incoming connections of a neuron. The internal event may be triggered by an external signal and/or internally by the neuron. A reinforcement signal may be used to trigger an internal event of a neuron in order to perform synaptic updates without necessitating post-synaptic response. An external event may be defined in order to deliver response of the neuron to desired targets. The external and internal events may be combined into a composite event configured to effectuate connection update and spike delivery to post-synaptic target. The scope of the internal event may comprise the respective neuron and does not extend to other neurons of the network. Conversely, the scope of the external event may extend to other neurons of the network via, for example, post-synaptic spike delivery.
摘要翻译：可以实现人造神经网络中基于事件的更新。可以定义内部事件以便更新神经元的传入连接。内部事件可能由外部信号和/或内部由神经元触发。加强信号可以用于触发神经元的内部事件，以便执行突触更新，而不需要突触后响应。可以定义外部事件以便将神经元的响应递送到期望的目标。外部和内部事件可以组合成组合事件，配置为实现连接更新和尖峰传递到突触后目标。内部事件的范围可以包括相应的神经元，并且不延伸到网络的其他神经元。相反，外部事件的范围可以通过例如突触后尖峰传递来延伸到网络的其他神经元。

9. 发明授权

US09256215B2 Apparatus and methods for generalized state-dependent learning in spiking neuron networks 有权
标题翻译：用于在尖峰神经元网络中进行广义状态依赖学习的装置和方法
公开(公告)号：US09256215B2
公开(公告)日：2016-02-09
申请号：US13560902
申请日：2012-07-27
申请人： Oleg Sinyavskiy , Filip Ponulak
发明人： Oleg Sinyavskiy , Filip Ponulak
IPC分类号： G06N5/00 , G06F1/00 , G05B13/02 , G06N3/04
CPC分类号： G05B13/025 , G06N3/049
摘要： Generalized state-dependent learning framework in artificial neuron networks may be implemented. A framework may be used to describe plasticity updates of neuron connections based on connection state term and neuron state term. The state connections within the network may be updated based on inputs and outputs to/from neurons. The input connections of a neuron may be updated using connection traces comprising a time-history of inputs provided via the connections. Weights of the connections may be updated and connection state may be time varying. The updated weights may be determined using a rate of change of the trace and a term comprising a product of a per-neuron contribution and a per-connection contribution configured to account for the state time-dependency. 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广义状态依赖学习框架。可以使用框架来描述基于连接状态项和神经元状态项的神经元连接的可塑性更新。可以基于对神经元的输入和输出来更新网络内的状态连接。可以使用包括通过连接提供的输入的时间历史的连接迹线来更新神经元的输入连接。可以更新连接的权重，并且连接状态可能是时变的。可以使用跟踪的变化率和包括每个神经元贡献的乘积和被配置为考虑状态时间依赖性的每个连接贡献的项来确定更新的权重。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。

10. 发明申请

US20130325768A1 STOCHASTIC SPIKING NETWORK LEARNING APPARATUS AND METHODS 有权
标题翻译： STOCHASTIC SPIKEING网络学习设备和方法
公开(公告)号：US20130325768A1
公开(公告)日：2013-12-05
申请号：US13487533
申请日：2012-06-04
申请人： Oleg Sinyavskiy , Olivier Coenen
发明人： Oleg Sinyavskiy , Olivier Coenen
IPC分类号： G06F15/18
CPC分类号： G05B13/027 , G06N3/049
摘要： Generalized learning rules may be implemented. A framework may be used to enable adaptive spiking neuron 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 time-averaged 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 spiking neuron 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 task.
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加标神经元信号处理系统，以灵活地组合不同的学习规则（受监督，无监督，强化学习）与不同的方法（在线或批量学习）。广义学习框架可以采用时间平均的性能函数作为学习措施，从而实现模块化架构，其中学习任务与控制任务分离，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。广义加标神经元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识别该任务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