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。

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：US20140229411A1

公开(公告)日：2014-08-14

申请号：US13763005

申请日：2013-02-08

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.

Abstract translation: 响应于时间上接近的特征学习的装置和方法。 在一个实施方案中，图像处理装置在加标神经元网络中利用双模态尖峰时间相关可塑性。 基于神经元对输入帧的响应，双模式可塑性机制用于抑制递送当前输入帧的突触连接并且加强递送先前和/或后续输入帧的突触连接。 近同期输入的抑制阻止了正反馈回路的创建，并提供了网络响应归一化的机制。