-
公开(公告)号：US5157738A
公开(公告)日：1992-10-20
申请号：US629393
申请日：1990-12-18
IPC分类号： G06N3/04
CPC分类号： G06K9/6222 , G06N3/0409
摘要： An improved ART2 network provides fast and intermediate learning. The network combines analog and binary coding functions. The analog portion encodes the recent past while the binary portion retains the distant past. LTM weights that fall below a threshold remain below threshold at all future times. The suprathreshold LTM weights track a time average of recent input patterns. LTM weight adjustment (update) provides fast commitment and slow recoding. The network incorporates these coding features while achieving an increase in computational efficiency of two to three orders of magnitude over prior analog ART systems.
摘要翻译： 改进的ART2网络提供快速和中级学习。 该网络结合了模拟和二进制编码功能。 模拟部分编码最近的过去，而二进制部分保留了远处的过去。 低于阈值的LTM权重在未来所有时间都保持低于阈值。 超阈值LTM权重跟踪最近输入模式的时间平均值。 LTM重量调整（更新）提供快速承诺和慢速重新编码。 该网络结合了这些编码特征，同时实现了比现有的模拟ART系统提高了两到三个数量级的计算效率。
-
公开(公告)号：US5214715A
公开(公告)日：1993-05-25
申请号：US648653
申请日：1991-01-31
IPC分类号： G06N3/04
CPC分类号： G06K9/6222 , G06N3/0409
摘要： An A pattern recognition subsystem responds to an A feature representation input to select A-category-representation and predict a B-category-representation and its associated B feature representation input. During learning trials, a predicted B-category-representation is compared to that obtained through a B pattern recognition subsystem. With mismatch, a vigilance parameter of the A-pattern-recognition subsystem is increased to cause reset of the first-category-representation selection. Inputs to the pattern recognition subsystems may be preprocessed to complement code the inputs.
摘要翻译： A模式识别子系统响应A特征表示输入以选择A类别表示并预测B类别表示及其相关联的B特征表示输入。 在学习试验期间，将预测的B类别表示与通过B模式识别子系统获得的B类别表示进行比较。 通过不匹配，A模式识别子系统的警戒参数增加，导致第一类别表示选择的重置。 可以对模式识别子系统的输入进行预处理以对输入进行补码。
-
3.发明授权System for self-organization of stable category recognition codes for analog input patterns 失效用于模拟输入模式的稳定类别识别代码的自组织系统
公开(公告)号：US4914708A
公开(公告)日：1990-04-03
申请号：US64764
申请日：1987-06-19
CPC分类号： G06K9/4628 , G06N3/0409
摘要： A neural network includes a feature representation field which receives input patterns. Signals from the feature representation field select a category from a category representation field through a first adaptive filter. Based on the selected category, a template pattern is applied to the feature representation field, and a match between the template and the input is determined. If the angle between the template vector and a vector within the representation field is too great, the selected category is reset. Otherwise the category selection and template pattern are adapted to the input pattern as well as the previously stored template. A complex representation field includes signals normalized relative to signals across the field and feedback for pattern contrast enhancement.
摘要翻译： 神经网络包括接收输入模式的特征表示场。 来自特征表示字段的信号通过第一自适应滤波器从类别表示字段中选择一个类别。 基于所选择的类别，将模板模式应用于特征表示字段，并且确定模板和输入之间的匹配。 如果模板向量与表示域中的向量之间的角度太大，则所选类别被重置。 否则，类别选择和模板模式适应于输入模式以及先前存储的模板。 复合表示场包括相对于场上的信号归一化的信号和用于图案对比度增强的反馈。
-
4.发明授权
公开(公告)号：US5311601A
公开(公告)日：1994-05-10
申请号：US761759
申请日：1991-11-04
CPC分类号： G06K9/6222 , G06N3/0409
摘要： In a pattern recognition system, input signals are applied to a short term feature representation field of nodes. A pattern from the short term feature representation field selects at least one category node in a category representation field. The selected category then generates a template pattern. With an insufficient match between the input pattern and template pattern, the category selection is reset. Category selection is based on selection weights which are initially set equal to long term memory weights. After reset, however, selections weights are reduced. Reduction is greatest at those nodes where excitation in F.sub.2 was greater prior to reset. The category representation field is of the same form as the field which receives the input and may itself serve as an input to a higher level pattern recognition system.
摘要翻译： PCT No.PCT / US91 / 00261 Sec。 371日期：1991年11月4日 102（e）1991年11月4日的PCT日期1991年1月11日PCT。在模式识别系统中，输入信号被应用于节点的短期特征表示场。 来自短期特征表示字段的模式在类别表示字段中选择至少一个类别节点。 所选类别然后生成模板模式。 由于输入模式和模板模式之间的匹配不足，重新设置类别选择。 类别选择基于最初设置为等于长期记忆权重的选择权重。 然而，复位后，选择权重减少。 在复位之前，F2中的激励较大的那些节点的衰减最大。 类别表示字段与接收输入的字段具有相同的形式，并且本身可以用作对较高级别模式识别系统的输入。
-
公开(公告)号：US5142590A
公开(公告)日：1992-08-25
申请号：US644685
申请日：1991-01-22
CPC分类号： G06K9/6222
摘要： A self-categorizing pattern recognition system includes an adaptive filter for selecting a category in response to an input pattern. A template is then generated in response to the selected category and a coincident pattern indicating the intersection between the expected pattern and the input pattern is generated. The ratio between the number of elements and the coincident pattern to the number of elements in the input pattern determines whether the category is reset. If the category is not reset, the adaptive filter and template may be modified in response to the coincident pattern. Reset of the selected category is inhibited if no expected pattern is generated. Weighting of the adaptive filter in response to a coincident pattern is inversely related to the number of elements in the input pattern. The selected categories reset where a reset function is less than a vigilance parameter which may be varied in response to teaching events.
摘要翻译： 自分类模式识别系统包括用于响应于输入模式选择类别的自适应滤波器。 然后响应于所选择的类别生成模板，并且生成指示预期图案和输入图案之间的交点的重合图案。 元素数量和重合模式与输入模式中的元素数量之间的比率决定了类别是否被重置。 如果该类别不被重置，则可以响应于重合模式来修改自适应滤波器和模板。 如果不产生预期的模式，则禁止所选类别的复位。 响应于一致的图案的自适应滤波器的权重与输入图案中的元素的数量成反比。 所选择的类别在复位功能小于可响应于教学事件而变化的警戒参数的情况下重置。
-
6.发明授权System for self-organization of stable category recognition codes for analog input patterns 失效用于模拟输入模式的稳定类别识别代码的自组织系统
公开(公告)号：US5133021A
公开(公告)日：1992-07-21
申请号：US486095
申请日：1990-02-28
申请人： Gail Carpenter , Stephen Grossberg
发明人： Gail Carpenter , Stephen Grossberg
CPC分类号： G06K9/6222 , G06N3/0409
摘要： A neural network includes a feature representation field which receives input patterns. Signals from the feature representative field select a category from a category representation field through a first adaptive filter. Based on the selected category, a template pattern is applied to the feature representation field, and a match between the template and the input is determined. If the angle between the template vector and a vector within the representation field is too great, the selected category is reset. Otherwise the category selection and template pattern are adapted to the input pattern as well as the previously stored template. A complex representation field includes signals normalized relative to signals across the field and feedback for pattern contrast enhancement.
摘要翻译： 神经网络包括接收输入模式的特征表示场。 来自特征代表字段的信号通过第一自适应滤波器从类别表示场中选择一个类别。 基于所选择的类别，将模板模式应用于特征表示字段，并且确定模板和输入之间的匹配。 如果模板向量与表示域中的向量之间的角度太大，则所选类别被重置。 否则，类别选择和模板模式适应于输入模式以及先前存储的模板。 复合表示场包括相对于场上的信号归一化的信号和用于图案对比度增强的反馈。
-
公开(公告)号：US5040214A
公开(公告)日：1991-08-13
申请号：US320806
申请日：1989-03-08
申请人： Stephen Grossberg , Michael Cohen
发明人： Stephen Grossberg , Michael Cohen
CPC分类号： G06K9/4623 , G10L15/16
摘要： A masking field network F.sub.2, is characterized through systematic computer simulations serves or a content addressable memory. Masking field network F.sub.2 receives input patterns from an adaptive filter F.sub.1 .fwdarw.F.sub.2 that is activated by a prior processing level F.sub.1. The network F.sub.2 activates compressed recognition close that are predictive with respect to the activation patterns flickering across F.sub.1, and competitively inhibits, or masks, codes which are unpredictive with respect to the F.sub.1 patterns. The masking field can simultaneously detect multiple groupings within its input patterns and assign activation weights to the recognition codes for these groupings which are predictive with respect to the contextual information embedded within the patterns and the prior learning of the network. Automatic rescaling of sensitivity of the masking field as the overall size of an input pattern changes, allows stronger activation of a code for the whole F.sub.1 pattern than for its salient parts. Network F.sub.2 also exhibits adaptive sharpening such that repetition of a familiar F.sub.1 pattern can tune the adaptive filter to elicit a more focal spatial activation of its F.sub.2 recognition code than does an unfamiliar input pattern. The F.sub.2 recognition code also becomes less distributed when an input pattern contains more contextual information on which to base an unambiguous prediction of the F.sub.1 pattern being processed. Thus the masking field embodies a real-time code to process the predictive evidence contained within its input patterns. Such capabilities are useful in speech recognition, visual object recognition, and cognitive information processinGOVERNMENT SUPPORTThis invention was made with Government support under AFOSR-85-0149 awarded by the Air Force. The Government has certain rights in this invention.
摘要翻译： 掩蔽场网络F2通过系统的计算机模拟服务或内容寻址存储器来表征。 掩蔽场网络F2从由先前处理级别F1激活的自适应滤波器F1-> F2接收输入模式。 网络F2激活关于激活模式在F1上闪烁的预测性的压缩识别关闭，并且竞争性地禁止或掩蔽相对于F1模式是不可预测的代码。 掩蔽字段可以同时检测其输入模式中的多个分组，并为这些分组的识别代码分配激活权重，这些分组对于嵌入在模式中的上下文信息和网络的先前学习是预测的。 随着输入图案的整体尺寸的变化，屏蔽场的灵敏度自动重新调整，允许对于整个F1模式的代码的强度比其突出部分更强。 网络F2还表现出自适应锐化，使得熟悉的F1模式的重复可以调整自适应滤波器以引发其F2识别码的更加焦点的空间激活，而不是不熟悉的输入模式。 当输入模式包含更多的基于正在处理的F1模式的明确预测的上下文信息时，F2识别码也变得较少分布。 因此，掩蔽字段包含实时代码来处理包含在其输入模式内的预测证据。 这样的功能在语音识别，视觉对象识别和认知信息处理中是有用的。
-
8.发明授权Massively parellel real-time network architectures for robots capable of self-calibrating their operating parameters through associative learning 失效用于通过关联学习自动校准其操作参数的机器人的大规模并行实时网络架构
公开(公告)号：US4852018A
公开(公告)日：1989-07-25
申请号：US1223
申请日：1987-01-07
IPC分类号： B25J9/16 , G05B19/414 , G06N3/00
CPC分类号： G06N3/008 , B25J9/163 , B25J9/1697 , G05B19/414 , G05B2219/33027 , G05B2219/42152 , Y10S706/904
摘要： A real-time network enables robots to accurately learn sensory motor transformation and to self-train and self-calibrate operating parameters after accidents or with wear. Combinations of visual and present position signals are used to relearn a target position map. Target positions in body-centered. visually activated coordinates are mapped into target positions in motor coordinates which are compared with present positions in motor coordinates to generate motor commands. Feedback provides calibrated error signals for adjustment of learned gain with changes in the system due to aging, accidents and the like. A series of prestored motor commands may be performed with a later "go" command.
摘要翻译： 实时网络使机器人能够准确地学习感觉运动转换，并在事故或磨损后自我训练和自校准操作参数。 使用视觉和当前位置信号的组合来重新学习目标位置图。 以身体为中心的目标职位 视觉激活的坐标映射到电机坐标中的目标位置，与电机坐标中的当前位置进行比较，以产生电机命令。 反馈提供校准误差信号，用于调整由于老化，事故等引起的系统变化的学习增益。 可以使用稍后的“去”命令来执行一系列预先存储的马达命令。
-
公开(公告)号：US4803736A
公开(公告)日：1989-02-07
申请号：US102018
申请日：1987-07-23
申请人： Stephen Grossberg , Ennio Mingolla
发明人： Stephen Grossberg , Ennio Mingolla
CPC分类号： G06T7/0083 , G06K9/4628
摘要： Network interactions within a Boundary Contour (BC) System, a Feature Contour (FC) System, and an Object Recognition (OR) System are employed to provide a computer vision system capable of recognizing emerging segmentations. The BC System is defined by a hierarchy of orientationally tuned interactions, which can be divided into two successive subsystems called the OC filter and the CC loop. The OC filter contains oriented receptive fields or masks, which are sensitive to different properties of image contrasts. The OC filter generates inputs to the CC loop, which contains successive stages of spatially shore-range competitive interactions and spatially long-range cooperative interactions. Feedback between the competitive and cooperative stages synthesizes a global context-sensitive segmentation from among the many possible groupings of local featural elements.
摘要翻译： 使用边界轮廓（BC）系统，特征轮廓（FC）系统和对象识别（OR）系统中的网络交互来提供能够识别新出现的分段的计算机视觉系统。 BC系统由定向调谐的相互作用的层次结构定义，其可以被分成称为OC滤波器和CC循环的两个连续的子系统。 OC滤波器包含对图像对比度的不同特性敏感的定向接收场或掩模。 OC滤波器产生CC循环的输入，其包含空间岸范围竞争性相互作用和空间长距离合作交互的连续阶段。 竞争和合作阶段之间的反馈从局部自然元素的许多可能的分组合成全局上下文敏感分割。
-
-
-
-
-
-
-
-
搜索结果
9 条记录 (耗时 0.029 秒)
