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

US10726337B1 Method and apparatus for emulation of neuromorphic hardware including neurons and synapses connecting the neurons 有权
公开(公告)号：US10726337B1
公开(公告)日：2020-07-28
申请号：US15143466
申请日：2016-04-29
申请人： HRL LABORATORIES, LLC
发明人： Corey M. Thibeault , Narayan Srinivasa
IPC分类号： G06N3/10 , G06N3/08
摘要： In a method for emulation of neuromorphic hardware on a computer processor, the neuromorphic hardware including computing circuits, the computing circuits including neurons and synapses connecting the neurons, the neurons being configured to communicate to each other through the synapses via spikes, the computing circuits being configured to execute in parallel in increments of time, the method includes, for each said time increment, emulating processing of the synapses, emulating processing of the neurons, and recording by the processor the next ones of the spikes for a subset of the neurons on a non-transitory physical medium. The processing of the synapses includes receiving previous ones of the spikes at presynaptic ends of the synapses, and transmitting the received previous ones of the spikes to postsynaptic ends of the synapses. The processing of the neurons includes receiving current ones of the spikes and generating next ones of the spikes.

2. 发明授权

US10096385B1 System and method for model-based estimation and control of epidural spinal cord stimulation 有权
公开(公告)号：US10096385B1
公开(公告)日：2018-10-09
申请号：US15219162
申请日：2016-07-25
申请人： HRL Laboratories, LLC
发明人： Corey M. Thibeault , Narayan Srinivasa
IPC分类号： A61N1/36 , G16H50/50 , A61N1/378 , G06F19/00
摘要： Described is a system for controlling epidural spinal cord stimulation. Using an Unscented Kalman Filter (UKF), the system receives sensed physiological signals from a subject and, based on the sensed physiological signals, estimating an unobservable state of a target area on the subject. A central pattern generator is then used to generate a stimulation pattern based on the unobservable state. The stimulation pattern is applied to the target area (e.g., spinal cord) of the subject using an electrode array. Receiving feedback, the UKF continuously updates a model of the spinal cord, which results in adjustment of the stimulation pattern as necessary.

3. 发明申请

US20150302296A1 PLASTIC ACTION-SELECTION NETWORKS FOR NEUROMORPHIC HARDWARE 审中-公开
标题翻译：用于神经网络硬件的塑料动作选择网络
公开(公告)号：US20150302296A1
公开(公告)日：2015-10-22
申请号：US13896110
申请日：2013-05-16
申请人： HRL LABORATORIES, LLC
发明人： Corey M. Thibeault , Narayan Srinivasa
IPC分类号： G06N3/08 , G06N3/04
CPC分类号： G06N3/08 , G06N3/04 , G06N3/049 , G06N20/00
摘要： A neural model for reinforcement-learning and for action-selection includes a plurality of channels, a population of input neurons in each of the channels, a population of output neurons in each of the channels, each population of input neurons in each of the channels coupled to each population of output neurons in each of the channels, and a population of reward neurons in each of the channels. Each channel of a population of reward neurons receives input from an environmental input, and is coupled only to output neurons in a channel that the reward neuron is part of. If the environmental input for a channel is positive, the corresponding channel of a population of output neurons are rewarded and have their responses reinforced, otherwise the corresponding channel of a population of output neurons are punished and have their responses attenuated.
摘要翻译：用于加强学习和动作选择的神经模型包括多个通道，每个通道中的输入神经元群体，每个通道中的输出神经元群，每个通道中的输入神经元的每个群体耦合到每个信道中的每个输出神经元的群体，以及每个信道中的一群奖励神经元。奖励神经元群体的每个通道从环境输入接收输入，并且仅耦合到奖励神经元属于其中的一个通道中的输出神经元。如果通道的环境输入为正，输出神经元群体的相应通道将得到奖励，并加强其响应，否则输出神经元群体的相应通道受到惩罚并使其响应减弱。

4. 发明授权

US09349092B2 Neural network for reinforcement learning 有权
标题翻译：加强学习的神经网络
公开(公告)号：US09349092B2
公开(公告)日：2016-05-24
申请号：US14293928
申请日：2014-06-02
申请人： HRL LABORATORIES LLC
发明人： Corey M. Thibeault , Narayan Srinivasa
IPC分类号： G06N3/08 , G06N3/04 , G06N99/00
CPC分类号： G06N3/08 , G06N3/04 , G06N3/049 , G06N99/005
摘要： A neural model for reinforcement-learning and for action-selection includes a plurality of channels, a population of input neurons in each of the channels, a population of output neurons in each of the channels, each population of input neurons in each of the channels coupled to each population of output neurons in each of the channels, and a population of reward neurons in each of the channels. Each channel of a population of reward neurons receives input from an environmental input, and is coupled only to output neurons in a channel that the reward neuron is part of. If the environmental input for a channel is positive, the corresponding channel of a population of output neurons are rewarded and have their responses reinforced, otherwise the corresponding channel of a population of output neurons are punished and have their responses attenuated.
摘要翻译：用于加强学习和动作选择的神经模型包括多个通道，每个通道中的输入神经元群体，每个通道中的输出神经元群，每个通道中的输入神经元的每个群体耦合到每个信道中的每个输出神经元的群体，以及每个信道中的一群奖励神经元。奖励神经元群体的每个通道从环境输入接收输入，并且仅耦合到奖励神经元属于其中的一个通道中的输出神经元。如果通道的环境输入为正，输出神经元群体的相应通道将得到奖励，并加强其响应，否则输出神经元群体的相应通道受到惩罚并使其响应减弱。

5. 发明授权

US10824871B1 Method and apparatus for obtaining unique signatures for a space through compressed imaging and semi-repeated movements 有权
公开(公告)号：US10824871B1
公开(公告)日：2020-11-03
申请号：US15159488
申请日：2016-05-19
申请人： HRL Laboratories, LLC
发明人： Corey M. Thibeault , Narayan Srinivasa
IPC分类号： G06K9/00 , G06K9/62 , H04N19/85
摘要： Described is a system and method for generating a unique signature for a space. During operation, the system causes a mobile platform to make one or more passes through the space along a repeatable path. While moving through the space, the system captures an image of the space around the mobile platform. A filter is applied to the image to generate vertical bins, the vertical bins being one-dimensional vectors of the space around the mobile platform. The one-dimensional vectors are combined over time to create a two-dimensional trace, with the two-dimensional trace being a unique signature for the space.

6. 发明授权

US10166394B1 Device and method to automatically tune the nerve stimulation pattern of a sensory-feedback capable prosthesis 有权
公开(公告)号：US10166394B1
公开(公告)日：2019-01-01
申请号：US15295657
申请日：2016-10-17
申请人： HRL Laboratories, LLC
发明人： Heiko Hoffmann , Jaehoon Choe , Corey M. Thibeault
IPC分类号： A61N1/36 , A61B5/11 , A61B5/00
摘要： Described is a system for automatically tuning the sensor feedback of a prosthetic device. The system comprises an electrode or plurality of electrodes in contact with a peripheral nerve of a user wearing a prosthetic device for administering the sensory feedback and an additional stimulus that evokes a muscle response in the user. A sensor is used to measure the muscle response. One or more processors generate a current stimulation pattern that encodes a posture of the prosthetic device. The current stimulation pattern is used in a spinal cord simulation to produce predicted muscle activations. Using the muscle response and the predicted muscle activations, an adjusted stimulation pattern is determined.

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