利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

132 条记录 (耗时 0.025 秒)

    Multi-layer development network having in-place learning
    71.
    发明授权
    Multi-layer development network having in-place learning 有权
    具有就地学习的多层开发网络

    公开(公告)号：US07711663B2

    公开(公告)日：2010-05-04

    申请号：US11728711

    申请日：2007-03-27

    申请人： Juyang Weng

    发明人： Juyang Weng

    IPC分类号： G06F15/18

    CPC分类号： G06N3/08 ,  G06K9/4623

    摘要： An in-place learning algorithm is provided for a multi-layer developmental network. The algorithm includes: defining a sample space as a plurality of cells fully connected to a common input; dividing the sample space into mutually non-overlapping regions, where each region is a represented by a neuron having a single feature vector; and estimating a feature vector of a given neuron by an amnesic average of an input vector weighted by a response of the given neuron, where amnesic is a recursive computation of the input vector weighted by the response such that the direction of the feature vector and the variance of signal in the region projected onto the feature vector are both recursively estimated with plasticity scheduling.

    摘要翻译： 为多层开发网络提供了就地学习算法。 该算法包括：将样本空间定义为完全连接到公共输入的多个单元; 将样本空间划分为相互不重叠的区域，其中每个区域由具有单个特征向量的神经元表示; 以及通过由所述给定神经元的响应加权的输入向量的遗忘平均值来估计给定神经元的特征向量，其中，所述输入矢量是由所述响应加权的所述输入向量的递归计算，使得所述特征向量和 投影到特征向量上的区域中的信号方差都用可塑性调度递归地估计。

    Representation and retrieval of images using context vectors derived from image information elements
    72.
    发明授权
    Representation and retrieval of images using context vectors derived from image information elements 失效
    使用从图像信息元素导出的上下文向量来表示和检索图像

    公开(公告)号：US07072872B2

    公开(公告)日：2006-07-04

    申请号：US10868538

    申请日：2004-06-14

    申请人： William R. Caid ,  Robert Hecht-Neilsen

    发明人： William R. Caid ,  Robert Hecht-Neilsen

    IPC分类号： G06F15/18

    CPC分类号： G06F17/30265 ,  G06F17/30256 ,  G06F17/3061 ,  G06K9/4623

    摘要： Image features are generated by performing wavelet transformations at sample points on images stored in electronic form. Multiple wavelet transformations at a point are combined to form an image feature vector. A prototypical set of feature vectors, or atoms, is derived from the set of feature vectors to form an “atomic vocabulary.” The prototypical feature vectors are derived using a vector quantization method, e.g., using neural network self-organization techniques, in which a vector quantization network is also generated. The atomic vocabulary is used to define new images. Meaning is established between atoms in the atomic vocabulary. High-dimensional context vectors are assigned to each atom. The context vectors are then trained as a function of the proximity and co-occurrence of each atom to other atoms in the image. After training, the context vectors associated with the atoms that comprise an image are combined to form a summary vector for the image. Images are retrieved using a number of query methods, e.g., images, image portions, vocabulary atoms, index terms. The user's query is converted into a query context vector. A dot product is calculated between the query vector and the summary vectors to locate images having the closest meaning. The invention is also applicable to video or temporally related images, and can also be used in conjunction with other context vector data domains such as text or audio, thereby linking images to such data domains.

    摘要翻译： 通过在以电子形式存储的图像上的采样点处执行小波变换来生成图像特征。 将点处的多个小波变换组合以形成图像特征向量。 特征向量或原子的原型集是从特征向量集合中导出的，以形成“原子词汇”。 使用矢量量化方法导出原型特征向量，例如使用其中也产生矢量量化网络的神经网络自组织技术。 原子词汇用于定义新图像。 在原子词汇中的原子之间建立意义。 高维上下文向量分配给每个原子。 然后将上下文矢量作为每个原子与图像中其他原子的邻近和共现的函数进行训练。 在训练之后，与构成图像的原子相关联的上下文向量被组合以形成图像的汇总向量。 使用许多查询方法（例如，图像，图像部分，词汇原子，索引项）来检索图像。 用户的查询被转换为查询上下文向量。 在查询向量和汇总向量之间计算点积，以定位具有最接近意义的图像。 本发明也适用于视频或时间相关的图像，并且还可以与诸如文本或音频的其他上下文矢量数据域一起使用，从而将图像链接到这样的数据域。

    Neurodynamic model of the processing of visual information
    73.
    发明申请
    Neurodynamic model of the processing of visual information 审中-公开
    神经动力学模型的视觉信息处理

    公开(公告)号：US20030228054A1

    公开(公告)日：2003-12-11

    申请号：US10425994

    申请日：2003-04-30

    申请人： Siemens Aktiengesellshaft

    发明人： Gustavo Deco

    IPC分类号： G06K009/00 ,  G06K009/62

    CPC分类号： G06K9/4623 ,  G06N3/04

    摘要： The model is a third generation neurosimulator. It has a plurality of areas whose functions can be identified with the functions of the areas of the dorsal and ventral path of the visual cortex of the human brain. Feedback is provided between different areas during processing. There is additionally provided competition for attention between different features and/or different spatial regions. The model is very flexibly suitable for image processing. It simulates natural human image processing and explains many experimentally observed phenomena.

    摘要翻译： 该模型是第三代神经刺激器。 它具有多个区域，其功能可以用人脑视觉皮层的背侧和腹侧路径的区域的功能来识别。 处理过程中不同区域之间提供反馈。 另外还提​​供了不同特征和/或不同空间区域之间的注意竞争。 该模型非常灵活地适用于图像处理。 它模拟自然人类图像处理，并解释了许多实验观察到的现象。

    Pattern recognition method using fuzzy neuron
    74.
    发明授权
    Pattern recognition method using fuzzy neuron 失效
    模糊识别方法使用模糊神经元

    公开(公告)号：US5592564A

    公开(公告)日：1997-01-07

    申请号：US429634

    申请日：1995-04-27

    申请人： Fumiaki Shigeoka ,  Masanari Oh

    发明人： Fumiaki Shigeoka ,  Masanari Oh

    IPC分类号： G06F9/44 ,  G06F15/18 ,  G06G7/12 ,  G06G7/60 ,  G06K9/46 ,  G06K9/66 ,  G06K9/68 ,  G06N3/04 ,  G06N7/02 ,  G06N99/00 ,  G06T7/00 ,  G06K9/62

    CPC分类号： G06K9/4623 ,  G06N3/0436

    摘要： A method for determining whether a fuzzy symbol matches a predetermined reference pattern by generating membership functions that collectively represent a reference pattern having identifying features; sampling the fuzzy symbol to generate an input pattern representative of the fuzzy symbol; transforming the input pattern to generate an inverted input pattern; comparing the input pattern with a first membership function to determine a first quantity of identifying features of the reference pattern that are present in the fuzzy symbol; comparing the inverted input pattern with a second membership function to determine a second quantity of identifying features of the reference pattern that are present in the fuzzy symbol; and determining that the fuzzy symbol matches the reference pattern if the first and second quantities are sufficiently high.

    摘要翻译： 一种用于通过产生共同表示具有识别特征的参考图案的隶属函数来确定模糊符号是否匹配预定参考图案的方法; 对模糊符号进行采样以产生代表模糊符号的输入模式; 变换输入图案以产生反相输入图案; 将输入模式与第一隶属度函数进行比较，以确定存在于模糊符号中的参考模式的识别特征的第一数量; 将所述反相输入模式与第二隶属函数进行比较，以确定存在于所述模糊符号中的参考模式的识别特征的第二数量; 以及如果所述第一和第二数量足够高，则确定所述模糊符号与所述参考图案匹配。

    SYSTEMS AND METHODS FOR ANALYZING REMOTE SENSING IMAGERY
    76.
    发明申请
    SYSTEMS AND METHODS FOR ANALYZING REMOTE SENSING IMAGERY 审中-公开

    公开(公告)号：US20190213412A1

    公开(公告)日：2019-07-11

    申请号：US16353345

    申请日：2019-03-14

    申请人： Cape Analytics, Inc.

    发明人： Ryan KOTTENSTETTE ,  Peter LORENZEN ,  Suat GEDIKLI

    IPC分类号： G06K9/00 ,  G06K9/62 ,  G06K9/46

    CPC分类号： G06K9/00637 ,  G06K9/4623 ,  G06K9/627 ,  H04N5/332

    摘要： Disclosed systems and methods relate to remote sensing, deep learning, and object detection. Some embodiments relate to machine learning for object detection, which includes, for example, identifying a class of pixel in a target image and generating a label image based on a parameter set. Other embodiments relate to machine learning for geometry extraction, which includes, for example, determining heights of one or more regions in a target image and determining a geometric object property in a target image. Yet other embodiments relate to machine learning for alignment, which includes, for example, aligning images via direct or indirect estimation of transformation parameters.

    LOCATION PROCESSOR FOR INFERENCING AND LEARNING BASED ON SENSORIMOTOR INPUT DATA
    77.
    发明申请
    LOCATION PROCESSOR FOR INFERENCING AND LEARNING BASED ON SENSORIMOTOR INPUT DATA 审中-公开

    公开(公告)号：US20180276464A1

    公开(公告)日：2018-09-27

    申请号：US15934795

    申请日：2018-03-23

    申请人： Numenta, Inc.

    发明人： Jeffrey C. Hawkins ,  Marcus Anthony Lewis

    IPC分类号： G06K9/00 ,  G06N5/04 ,  G06K9/62

    CPC分类号： G06K9/00577 ,  G06K9/00979 ,  G06K9/3241 ,  G06K9/4623 ,  G06K9/4628 ,  G06K9/6215 ,  G06N3/0454 ,  G06N3/08 ,  G06N5/04

    摘要： An inference system performs inference, such as object recognition, based on sensory inputs generated by sensors and control information associated with the sensory inputs. The sensory inputs describe one or more features of the objects. The control information describes movement of the sensors or known locations of the sensors relative to a reference point. For a particular object, an inference system learns a set of object-location representations of the object. An object-location representation is a unique characterization of an object-centric location relative to the particular object. The inference system also learns a set of feature-location representations associated with the object-location representation that indicate presence of features at the corresponding object-location pair. The inference system can perform inference on an unknown object by identifying candidate object-location representations consistent with feature-location representations observed from the sensory input data and control information.