公开(公告)号：US20140372355A1

公开(公告)日：2014-12-18

申请号：US14275663

申请日：2014-05-12

Applicant: BRAIN Corporation

Inventor： Eugene M. Izhikevich ,  Filip Piekniewski ,  Jayram Moorkanikara Nageswaran

IPC: G06N3/04 ,  G06N3/063

CPC classification number: G06N3/049 ,  G06N3/063 ,  G06N3/08

Abstract: Apparatus and methods for partial evaluation of synaptic updates in neural networks. In one embodiment, a pre-synaptic unit is connected to a several post synaptic units via communication channels. Information related to a plurality of post-synaptic pulses generated by the post-synaptic units is stored by the network in response to a system event. Synaptic channel updates are performed by the network using the time intervals between a pre-synaptic pulse, which is being generated prior to the system event, and at least a portion of the plurality of the post synaptic pulses. The system event enables removal of the information related to the portion of the post-synaptic pulses from the storage device. A shared memory block within the storage device is used to store data related to post-synaptic pulses generated by different post-synaptic nodes. This configuration enables memory use optimization of post-synaptic units with different firing rates.

Abstract translation: 用于部分评估神经网络中突触更新的装置和方法。 在一个实施例中，突触前单元经由通信信道连接到几个后突触单元。 与由突触后单元生成的多个突触后脉冲相关的信息由网络响应于系统事件存储。 突触信道更新由网络使用在系统事件之前产生的预触觉脉冲与多个突触后脉冲的至少一部分之间的时间间隔来执行。 系统事件使得能够从存储设备去除与突触后部分脉冲相关的信息。 存储设备内的共享存储器块用于存储与由不同的突触后节点产生的突触后脉冲相关的数据。 这种配置使得具有不同发射速率的突触后单元的存储器使用优化成为可能。

公开(公告)号：US20140365414A1

公开(公告)日：2014-12-11

申请号：US14466913

申请日：2014-08-22

Applicant: Brain Corporation

Inventor： Micah Richert ,  Filip Piekniewski ,  Eugene Izhikevich ,  Sach Sokol

IPC: G06N3/08

CPC classification number: G06K9/00711 ,  G06K9/4671 ,  G06N3/049 ,  G06N3/08 ,  G06T7/246 ,  G06T2207/10016

Abstract: Apparatus and methods for learning in response to temporally-proximate features. In one implementation, an image processing apparatus utilizes bi-modal spike timing dependent plasticity in a spiking neuron network. Based on a response by the neuron to a frame of input, the bi-modal plasticity mechanism is used to depress synaptic connections delivering the present input frame and to potentiate synaptic connections delivering previous and/or subsequent frames of input. The depression of near-contemporaneous input prevents the creation of a positive feedback loop and provides a mechanism for network response normalization.

公开(公告)号：US10860882B2

公开(公告)日：2020-12-08

申请号：US16042901

申请日：2018-07-23

Applicant: Brain Corporation

Inventor： Filip Piekniewski ,  Micah Richert ,  Dimitry Fisher

IPC: G06K9/46 ,  G06K9/48 ,  G06T7/90 ,  G06T7/20 ,  G06K9/00 ,  G06T3/00 ,  G06T7/246 ,  G06T7/285 ,  H04N9/797 ,  G06K9/32 ,  G06T7/292 ,  B25J9/16 ,  G01B11/14

Abstract: Apparatus and methods for detecting and utilizing saliency in digital images. In one implementation, salient objects may be detected based on analysis of pixel characteristics. Least frequently occurring pixel values may be deemed as salient. Pixel values in an image may be compared to a reference. Color distance may be determined based on a difference between reference color and pixel color. Individual image channels may be scaled when determining saliency in a multi-channel image. Areas of high saliency may be analyzed to determine object position, shape, and/or color. Multiple saliency maps may be additively or multiplicative combined in order to improve detection performance (e.g., reduce number of false positives). Methodologies described herein may enable robust tracking of objects utilizing fewer determination resources. Efficient implementation of the methods described below may allow them to be used for example on board a robot (or autonomous vehicle) or a mobile determining platform.

公开(公告)号：US10810456B2

公开(公告)日：2020-10-20

申请号：US15871862

申请日：2018-01-15

Applicant: Brain Corporation

Inventor： Filip Piekniewski ,  Micah Richert ,  Dimitry Fisher

IPC: G06K9/00 ,  G06K9/46 ,  G06K9/48 ,  G06T7/246 ,  G06T7/90 ,  G06T7/285 ,  H04N9/797 ,  G06K9/32 ,  G06T7/20 ,  G06T7/292 ,  B25J9/16 ,  G01B11/14 ,  G06T3/00

Abstract: Apparatus and methods for detecting and utilizing saliency in digital images. In one implementation, salient objects may be detected based on analysis of pixel characteristics. Least frequently occurring pixel values may be deemed as salient. Pixel values in an image may be compared to a reference. Color distance may be determined based on a difference between reference color and pixel color. Individual image channels may be scaled when determining saliency in a multi-channel image. Areas of high saliency may be analyzed to determine object position, shape, and/or color. Multiple saliency maps may be additively or multiplicative combined in order to improve detection performance (e.g., reduce number of false positives). Methodologies described herein may enable robust tracking of objects utilizing fewer determination resources. Efficient implementation of the methods described below may allow them to be used for example on board a robot (or autonomous vehicle) or a mobile determining platform.

公开(公告)号：US20200086494A1

公开(公告)日：2020-03-19

申请号：US16582302

申请日：2019-09-25

Applicant: Brain Corporation

Inventor： Dimitry Fisher ,  Cody Griffin ,  Micah Richert ,  Filip Piekniewski ,  Eugene Izhikevich ,  Jayram Moorkanikara Nageswaran ,  John Black

IPC: B25J9/16 ,  G05D1/02 ,  G06K9/00 ,  G06K9/46 ,  G06T7/11 ,  H04N5/33 ,  G05D1/00 ,  G08B21/20

Abstract: Systems and methods for automatic detection of spills are disclosed. In some exemplary implementations, a robot can have a spill detector comprising at least one optical imaging device configured to capture at least one image of a scene containing a spill while the robot moves between locations. The robot can process the at least one image by segmentation. Once the spill has been identified, the robot can then generate an alert indicative at least in part of a recognition of the spill.

公开(公告)号：US10282849B2

公开(公告)日：2019-05-07

申请号：US15627096

申请日：2017-06-19

Applicant: Brain Corporation

Inventor： Filip Piekniewski ,  Micah Richert ,  Dimitry Fisher ,  Patryk Laurent ,  Csaba Petre

IPC: G06T7/00 ,  G06T1/60 ,  G06T7/20 ,  G06T9/00 ,  G06F12/08

Abstract: Systems and methods for predictive/reconstructive visual object tracking are disclosed. The visual object tracking has advanced abilities to track objects in scenes, which can have a variety of applications as discussed in this disclosure. In some exemplary implementations, a visual system can comprise a plurality of associative memory units, wherein each associative memory unit has a plurality of layers. The associative memory units can be communicatively coupled to each other in a hierarchical structure, wherein data in associative memory units in higher levels of the hierarchical structure are more abstract than lower associative memory units. The associative memory units can communicate to one another supplying contextual data.

公开(公告)号：US20190061160A1

公开(公告)日：2019-02-28

申请号：US15997397

申请日：2018-06-04

Applicant: BRAIN CORPORATION

Inventor： Dimitry Fisher ,  Cody Griffin ,  Micah Richert ,  Filip Piekniewski ,  Eugene Izhikevich ,  Jayram Moorkanikara Nageswaran ,  John Black

IPC: B25J9/16 ,  G05D1/00 ,  G08B21/20 ,  G06K9/46 ,  G06T7/11 ,  G06K9/00 ,  H04N5/33

Abstract: Systems and methods for automatic detection of spills are disclosed. In some exemplary implementations, a robot can have a spill detector comprising at least one optical imaging device configured to capture at least one image of a scene containing a spill while the robot moves between locations. The robot can process the at least one image by segmentation. Once the spill has been identified, the robot can then generate an alert indicative at least in part of a recognition of the spill.

公开(公告)号：US10032280B2

公开(公告)日：2018-07-24

申请号：US14637164

申请日：2015-03-03

Applicant: Brain Corporation

Inventor： Filip Piekniewski ,  Micah Richert ,  Dimitry Fisher

IPC: G06T7/00 ,  G06K9/32 ,  G06K9/46 ,  G06T7/20 ,  H04N9/797 ,  G06K9/48 ,  G06T7/246 ,  G06T7/90

Abstract: Apparatus and methods for detecting and utilizing saliency in digital images. In one implementation, salient objects may be detected based on analysis of pixel characteristics. Least frequently occurring pixel values may be deemed as salient. Pixel values in an image may be compared to a reference. Color distance may be determined based on a difference between reference color and pixel color. Individual image channels may be scaled when determining saliency in a multi-channel image. Areas of high saliency may be analyzed to determine object position, shape, and/or color. Multiple saliency maps may be additively or multiplicative combined in order to improve detection performance (e.g., reduce number of false positives). Methodologies described herein may enable robust tracking of objects utilizing fewer determination resources. Efficient implementation of the methods described below may allow them to be used for example on board a robot (or autonomous vehicle) or a mobile determining platform.

公开(公告)号：US09239985B2

公开(公告)日：2016-01-19

申请号：US13922116

申请日：2013-06-19

Applicant: Brain Corporation

Inventor： Filip Piekniewski

IPC: G06E1/00 ,  G06E3/00 ,  G06F15/18 ,  G06G7/00 ,  G06N3/08 ,  G06N3/063 ,  G06N3/10 ,  G06N3/06 ,  G06N3/04

CPC classification number: G06N3/08 ,  G06N3/04 ,  G06N3/049 ,  G06N3/06 ,  G06N3/063 ,  G06N3/0635 ,  G06N3/10

Abstract: Apparatus and methods for processing inputs by one or more neurons of a network. The neuron(s) may generate spikes based on receipt of multiple inputs. Latency of spike generation may be determined based on an input magnitude. Inputs may be scaled using for example a non-linear concave transform. Scaling may increase neuron sensitivity to lower magnitude inputs, thereby improving latency encoding of small amplitude inputs. The transformation function may be configured compatible with existing non-scaling neuron processes and used as a plug-in to existing neuron models. Use of input scaling may allow for an improved network operation and reduce task simulation time.

Abstract translation: 用于由网络的一个或多个神经元处理输入的装置和方法。 基于多个输入的接收，神经元可以产生尖峰。 可以基于输入幅度来确定尖峰生成的延迟。 可以使用例如非线性凹变换来缩放输入。 缩放可以将神经元灵敏度增加到较低幅度的输入，从而改善小振幅输入的延迟编码。 转换函数可以被配置为与现有的非缩放神经元过程兼容，并且用作现有神经元模型的插件。 使用输入缩放可以允许改进的网络操作并减少任务模拟时间。

公开(公告)号：US09218563B2

公开(公告)日：2015-12-22

申请号：US13660982

申请日：2012-10-25

Applicant: Brain Corporation

Inventor： Botond Szatmary ,  Micah Richert ,  Eugene Izhikevich ,  Jayram Moorkanikara Nageswaran ,  Filip Piekniewski ,  Sach Sokol ,  Csaba Petre

IPC: G06E1/00 ,  G06E3/00 ,  G06F15/18 ,  G06G7/00 ,  G06N3/02 ,  G06F15/00 ,  G06F17/00 ,  G06N3/10

CPC classification number: G06N3/02 ,  G06N3/049 ,  G06N3/063 ,  G06N3/088

Abstract: Apparatus and methods for salient feature detection by a spiking neuron network. The network may comprise feature-specific units capable of responding to different objects (red and green color). The plasticity mechanism of the network may be configured based on difference between two similarity measures related to activity of different unit types obtained during network training. One similarity measure may be based on activity of units of the same type (red). Another similarity measure may be based on activity of units of one type (red) and another type (green). Similarity measures may comprise a cross-correlogram and/or mutual information determined over an activity window. During network operation, the activity based plasticity mechanism may be used to potentiate connections between units of the same type (red-red). The plasticity mechanism may be used to depress connections between units of different types (red-green). The plasticity mechanism may effectuate detection of salient features in the input.

Abstract translation: 通过尖峰神经元网络显着特征检测的装置和方法。 网络可以包括能够响应于不同对象（红色和绿色）的特征单元。 网络的可塑性机制可以基于网络训练过程中获得的不同单元类型的活动相关的两个相似性度量之间的差异进行配置。 一个相似性度量可以基于相同类型（红色）的单元的活动。 另一种相似性度量可以基于一种类型（红色）和另一种类型（绿色）的单位的活动。 相似性度量可以包括在活动窗口上确定的交叉相关图和/或相互信息。 在网络运行期间，基于活动的可塑性机制可用于加强相同类型（红 - 红）单元之间的连接。 可塑性机制可用于抑制不同类型（红 - 绿）单元之间的连接。 可塑性机制可能会影响输入中突出特征的检测。