专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

11. 发明申请

US20130325773A1 STOCHASTIC APPARATUS AND METHODS FOR IMPLEMENTING GENERALIZED LEARNING RULES 有权
标题翻译：实施一般学习规则的机器人和方法
公开(公告)号：US20130325773A1
公开(公告)日：2013-12-05
申请号：US13487499
申请日：2012-06-04
申请人： Oleg Sinyavskiy , Olivier J. M. D. Coenen
发明人： Oleg Sinyavskiy , Olivier J. M. D. Coenen
IPC分类号： G06F15/18
CPC分类号： G05B13/027 , G06N3/049 , 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 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. 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。可以使用框架来灵活地启用自适应信号处理系统，结合不同的学习规则（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。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。

12. 发明授权

US09104186B2 Stochastic apparatus and methods for implementing generalized learning rules 有权
标题翻译：随机设备和实现广义学习规则的方法
公开(公告)号：US09104186B2
公开(公告)日：2015-08-11
申请号：US13487499
申请日：2012-06-04
申请人： Oleg Sinyavskiy , Olivier J. M. D. Coenen
发明人： Oleg Sinyavskiy , Olivier J. M. D. Coenen
IPC分类号： G06F15/18 , G05B13/02 , G06N3/04 , G06N99/00
CPC分类号： G05B13/027 , G06N3/049 , 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 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. 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。可以使用框架来灵活地启用自适应信号处理系统，结合不同的学习规则（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。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。

13. 发明授权

US08990133B1 Apparatus and methods for state-dependent learning in spiking neuron networks 有权
标题翻译：用于加标神经元网络状态依赖学习的装置和方法
公开(公告)号：US08990133B1
公开(公告)日：2015-03-24
申请号：US13722769
申请日：2012-12-20
申请人： Filip Ponulak , Oleg Sinyavskiy
发明人： Filip Ponulak , Oleg Sinyavskiy
IPC分类号： G06N3/08 , G06N3/02
CPC分类号： G06N3/08 , G06N3/049
摘要： State-dependent supervised learning framework in artificial neuron networks may be implemented. A framework may be used to describe plasticity updates of neuron connections based on a connection state term and a neuron state term. Connection states may be updated based on inputs and outputs to and/or from neurons. The input connections of a neuron may be updated using input traces comprising a time-history of inputs provided via the connection. Weight of the connection may be updated and connection state may be time varying. The updated weights may be determined using a rate of change of the input 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 a per neuron basis, as opposed to a per-connection basis.
摘要翻译：可以实现人工神经元网络中的状态依赖监督学习框架。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。可以基于对神经元和/或神经元的输入和输出来更新连接状态。可以使用包括经由连接提供的输入的时间历史的输入轨迹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。可以使用输入跟踪的变化率来确定更新的权重，以及包括每个神经元贡献和被配置为考虑状态时间依赖性的每连接贡献的乘积的项。使用与事件相关的连接更改组件，可以在每个神经元的基础上执行连接更新，而不是基于每个连接。

14. 发明授权

US08943008B2 Apparatus and methods for reinforcement learning in artificial neural networks 有权
标题翻译：人工神经网络强化学习的装置和方法
公开(公告)号：US08943008B2
公开(公告)日：2015-01-27
申请号：US13489280
申请日：2012-06-05
申请人： Filip Ponulak , Oleg Sinyavskiy
发明人： Filip Ponulak , Oleg Sinyavskiy
IPC分类号： G06F15/18 , G06N3/08
CPC分类号： G06N3/08 , G05B13/027 , G06N3/049 , G06N99/005
摘要： Neural network apparatus and methods for implementing reinforcement learning. In one implementation, the neural network is a spiking neural network, and the apparatus and methods may be used for example to enable an adaptive signal processing system to effect focused exploration by associative adaptation, including providing a negative reward signal to the network, which may increase excitability of the neurons in combination with decrease in excitability of active neurons. In certain implementations, the increase is gradual and of smaller magnitude, compared to the excitability decrease. In some implementations, the increase/decrease of the neuron excitability is effectuated by increasing/decreasing an efficacy of the respective synaptic connections delivering presynaptic inputs into the neuron. The focused exploration may be achieved for instance by non-associative potentiation configured based at least on the input spike rate. The non-associative potentiation may further comprise depression of connections that provide input in excess of a desired limit.
摘要翻译：用于实施强化学习的神经网络装置和方法。在一个实现中，神经网络是加标神经网络，并且该装置和方法可以用于例如使得自适应信号处理系统能够通过关联适应来实现聚焦探索，包括向网络提供负回报信号，增加神经元的兴奋性与活性神经元的兴奋性降低相结合。在某些实施方案中，与兴奋性降低相比，增加是逐渐的和较小的幅度。在一些实施方案中，神经元兴奋性的增加/减少通过增加/减少将突触前输入递送到神经元中的各个突触连接的功效来实现。集中的探索可以例如通过至少基于输入尖峰率配置的非关联增强来实现。非关联增强可以进一步包括提供输入超过期望极限的连接的抑制。

15. 发明申请

US20140081895A1 SPIKING NEURON NETWORK ADAPTIVE CONTROL APPARATUS AND METHODS 有权
标题翻译： SPIKE神经网络自适应控制装置和方法
公开(公告)号：US20140081895A1
公开(公告)日：2014-03-20
申请号：US13623842
申请日：2012-09-20
申请人： Oliver Coenen , Oleg Sinyavskiy
发明人： Oliver Coenen , Oleg Sinyavskiy
IPC分类号： G06N3/08
CPC分类号： G06N3/08 , G05B13/027 , G06N3/049
摘要： Adaptive controller apparatus of a plant may be implemented. The controller may comprise an encoder block and a control block. The encoder may utilize basis function kernel expansion technique to encode an arbitrary combination of inputs into spike output. The controller may comprise spiking neuron network operable according to reinforcement learning process. The network may receive the encoder output via a plurality of plastic connections. The process may be configured to adaptively modify connection weights in order to maximize process performance, associated with a target outcome. The relevant features of the input may be identified and used for enabling the controlled plant to achieve the target outcome.
摘要翻译：可以实现工厂的自适应控制器装置。控制器可以包括编码器块和控制块。编码器可以利用基本功能的内核扩展技术来将输入的任意组合编码成尖峰输出。控制器可以包括根据加强学习过程可操作的加标神经元网络。网络可以通过多个塑料连接接收编码器输出。该过程可以被配置为自适应地修改连接权重，以便最大化与目标结果相关联的过程性能。输入的相关特征可以被识别并用于使被控制厂能够实现目标结果。

16. 发明授权

US09146546B2 Systems and apparatus for implementing task-specific learning using spiking neurons 有权
标题翻译：使用尖峰神经元实现特定任务学习的系统和设备
公开(公告)号：US09146546B2
公开(公告)日：2015-09-29
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： G06N3/04 , G05B13/02
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。

17. 发明申请

US20140032459A1 APPARATUS AND METHODS FOR GENERALIZED STATE-DEPENDENT LEARNING IN SPIKING NEURON NETWORKS 有权
标题翻译： SPIKE神经网络中广义状态依赖学习的设备与方法
公开(公告)号：US20140032459A1
公开(公告)日：2014-01-30
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： G06F15/18
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。

18. 发明申请

US20130325776A1 APPARATUS AND METHODS FOR REINFORCEMENT LEARNING IN ARTIFICIAL NEURAL NETWORKS 有权
标题翻译：人工神经网络加固学习的装置和方法
公开(公告)号：US20130325776A1
公开(公告)日：2013-12-05
申请号：US13489280
申请日：2012-06-05
申请人： Filip Ponulak , Oleg Sinyavskiy
发明人： Filip Ponulak , Oleg Sinyavskiy
IPC分类号： G06N3/08 , G05B13/00
CPC分类号： G06N3/08 , G05B13/027 , G06N3/049 , G06N99/005
摘要： Neural network apparatus and methods for implementing reinforcement learning. In one implementation, the neural network is a spiking neural network, and the apparatus and methods may be used for example to enable an adaptive signal processing system to effect focused exploration by associative adaptation, including providing a negative reward signal to the network, which may increase excitability of the neurons in combination with decrease in excitability of active neurons. In certain implementations, the increase is gradual and of smaller magnitude, compared to the excitability decrease. In some implementations, the increase/decrease of the neuron excitability is effectuated by increasing/decreasing an efficacy of the respective synaptic connections delivering presynaptic inputs into the neuron. The focused exploration may be achieved for instance by non-associative potentiation configured based at least on the input spike rate. The non-associative potentiation may further comprise depression of connections that provide input in excess of a desired limit.
摘要翻译：用于实施强化学习的神经网络装置和方法。在一个实现中，神经网络是加标神经网络，并且该装置和方法可以用于例如使得自适应信号处理系统能够通过关联适应来实现聚焦探索，包括向网络提供负回报信号，增加神经元的兴奋性与活性神经元的兴奋性降低相结合。在某些实施方案中，与兴奋性降低相比，增加是逐渐的和较小的幅度。在一些实施方案中，神经元兴奋性的增加/减少通过增加/减少将突触前输入递送到神经元中的各个突触连接的功效来实现。集中的探索可以例如通过至少基于输入尖峰率配置的非关联增强来实现。非关联增强可以进一步包括提供输入超过期望极限的连接的抑制。

19. 发明申请

US20130325774A1 LEARNING STOCHASTIC APPARATUS AND METHODS 审中-公开
标题翻译：学习机器人和方法
公开(公告)号：US20130325774A1
公开(公告)日：2013-12-05
申请号：US13487621
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： G06N3/049 , G05B13/027 , G06N3/08
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 non-associative transform of 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. The use of non-associative transformations, when employed in conjunction with gradient optimization methods, does not bias the performance function gradient, on a long-term averaging scale and may advantageously enable stochastic drift thereby facilitating exploration leading to faster convergence of learning process. When applied to spiking learning networks, transforming the performance function using a constant term, may lead to non-associative increase of synaptic connection efficacy thereby providing additional exploration mechanisms.
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）。广义学习框架可以使用时间平均性能函数的非关联变换作为学习措施，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。当与梯度优化方法结合使用时，使用非关联变换不会在长期平均尺度上偏置性能函数梯度，并且可以有利地实现随机漂移，从而便于探索，从而促进学习过程的更快的收敛。当应用于加速学习网络时，使用常数项来转换性能函数，可能导致突触连接功能的非关联性增加，从而提供额外的探索机制。

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