专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

31. 发明授权

EP0944021B1 Method and apparatus for training for generating and for adjusting a neuron 失效
标题翻译：用于产生和调节神经元的方法和设备
公开(公告)号：EP0944021B1
公开(公告)日：2005-05-11
申请号：EP99111038.8
申请日：1993-06-18
申请人： UNITED PARCEL SERVICE OF AMERICA, INC.
发明人： Moed, Michael C. , Lee, Chih-Ping, United Parcel Service of America
IPC分类号： G06K9/62
CPC分类号： G06K9/6274 , G06K9/6223 , G06K9/6272 , G06K9/6273

32. 发明授权

EP1197914B1 A training method and apparatus for creating a new neuron 失效
标题翻译：用于生成新的神经元的训练的方法和装置
公开(公告)号：EP1197914B1
公开(公告)日：2003-10-08
申请号：EP01125305.1
申请日：1993-06-18
申请人： UNITED PARCEL SERVICE OF AMERICA, INC.
发明人： Moed, Michael C. , Lee, Chih-Ping c/o United Parcel Serv.America Inc
IPC分类号： G06K9/66
CPC分类号： G06K9/6274 , G06K9/6223 , G06K9/6273 , G06N3/082

33. 发明公开

EP1199675A1 Method and apparatus for adjusting a neuron 失效
标题翻译： Verfahren undGerätzur Einstellung eines Neurons
公开(公告)号：EP1199675A1
公开(公告)日：2002-04-24
申请号：EP01115778.1
申请日：1993-06-18
申请人： UNITED PARCEL SERVICE OF AMERICA, INC.
发明人： Moed, Michael C. , Lee, Chih-Ping
IPC分类号： G06K9/66
CPC分类号： G06K9/6274 , G06K9/6223 , G06K9/6272 , G06K9/6273
摘要： A method for adjusting a neuron encompassing a plurality of feature vectors comprises the steps of characterizing the spatial distribution of said feature vectors, and spatially adjusting said neuron in accordance with the characterization of step (a). An apparatus for adjusting a neuron encompassing a plurality of feature vectors comprises characterizing means for characterizing the spatial distribution of said feature vectors, and adjusting means for spatially adjusting said neuron in accordance with the characterization by said characterizing means.
摘要翻译：一种用于调整包含多个特征向量的神经元的方法包括以下步骤：表征所述特征向量的空间分布，以及根据步骤（a）的表征空间调整所述神经元。用于调整包含多个特征向量的神经元的装置包括用于表征所述特征向量的空间分布的特征化装置，以及根据所述特征化装置的表征空间调整所述神经元的调整装置。

34. 发明授权

EP0325119B1 Apparatus for cumulative learning of internal representations in an n-dimensional coulomb network 失效
标题翻译：一种用于在n维“库仑”网络内部表示的累积学习。
公开(公告)号：EP0325119B1
公开(公告)日：1995-09-06
申请号：EP89100158.8
申请日：1989-01-05
申请人： NESTOR, INC.
发明人： Scofield, Christopher L.
IPC分类号： G06F15/76
CPC分类号： G06K9/6274 , G06N3/04 , G06N3/08

35. 发明公开

EP0191407A3 Parallel, multi-unit, adaptive, nonlinear pattern class separator and identifier 失效
标题翻译：并行，多单元，自适应，非线性模式分类器和识别器
公开(公告)号：EP0191407A3
公开(公告)日：1989-11-08
申请号：EP86101452.0
申请日：1986-02-05
申请人： NESTOR, INC.
发明人： Cooper, Leon N. , Elbaum, Charles , Reilly, Douglas L. , Scofield, Christopher L.
IPC分类号： G06K9/62
CPC分类号： G06K9/6292 , G06K9/6274
摘要： A system is disclosed for separating and identifying alasses of patterns or events which are not necessarily linearly separable. The patterns are represented by an input signal S. The system comprises (1) a plurality of classification inits, connected in parallel to receive the input signal S, and 2) a class selection device, responsive to the output signals broduced by the classification units, for producing a single butput response R representing the class of each respective battem. In a preferred embodiment each classification unit ncludes a pattern feature encoding device, responsive to the nput signal S, for producing an intermediate signal F i repre- bentative of the features contained in the pattern, and a battem classifier, responsive to the signal F i , for producing an output signal R i representative of the respective class of he pattern, as identified by the features encoded by the eature encoding device.

36. 发明公开

EP0325119A2 Apparatus for cumulative learning of internal representations in an n-dimensional coulomb network 失效
标题翻译：一种用于在n维“库仑”网络内部表示的累积学习。
公开(公告)号：EP0325119A2
公开(公告)日：1989-07-26
申请号：EP89100158.8
申请日：1989-01-05
申请人： NESTOR, INC.
发明人： Scofield, Christopher L.
IPC分类号： G06F15/76
CPC分类号： G06K9/6274 , G06N3/04 , G06N3/08
摘要： A learning algorithm for the N-dimensional Coulomb network is disclosed which is applicable to multi-layer networks. The central concept is to define a potential energy of a collection of memory sites. Then each memory site is an attractor of other memory sites. With the proper definition of attractive and repulsive potentials between various memory sites, it is possible to minimize the energy of the collection of memories. By this method, internal representations may be "built-up" one layer at a time.
Following the method of Bachmann et. al. a system is considered in which memories of events have already been recorded in a layer of cells. A method is found for the consolidation of the number of memories required to correctly represent the pattern environment. This method is shown to be applicable to a supervised learning paradigm in which pairs of input and output patterns are presented sequentially to the network. The resulting learning procedure develops internal representations in an incremental or cumulative fashion, from the layer closest to the input, to the output layer.
摘要翻译：对于N维库仑网络学习算法是游离缺失光盘所有可应用于多层网络。核心概念是定义存储网站的集合的势能。然后，每个存储站点是其他存储网站的吸引。随着各种存储站点之间的吸引力和排斥力潜力的适当定义，有可能减少的回忆收集的能量。通过这种方法，内部表示可以是“建成”一个层在一个时间。继Bachmann等的方法。人。系统被认为是哪个事件的记忆都已经被记录在细胞层。一种方法是找到的正确表示图案环境所需存储器的数量的合并。这种方法被证明是适用于其中对输入和输出模式的监督学习范例都按顺序到网络。将得到的学习过程开发出的内部表示中的增量或累积的方式，从该层最接近输入到输出层。

37. 发明公开

EP0037164A2 Self organising general pattern class separator and identifier 有权转让
标题翻译：自组织分离器和一般形式的类标识符。
公开(公告)号：EP0037164A2
公开(公告)日：1981-10-07
申请号：EP81300559.2
申请日：1981-02-11
申请人： NESTOR, INC.
发明人： Cooper, Leon N., Dr. , Elbaum, Charles, Dr. , Reilly, Douglas L.
IPC分类号： G06K9/62 , G06K9/64
CPC分类号： G06K9/6274
摘要： A system is provided for the separation into and the identification of classes of events wherein each of the events is represented by a signal vector comprising the signals s, sz...,sj...,sN. The system comprises a plurality of assemblies, each of the assemblies including a matrix of junction elements for respectively receiving as inputs the different respective signals of a vector. The junction elements provide a transfer of information Aijs,; i.e., the product of the transfer function of the element and the signal input applied thereto. The information transferred by the junction elements is summed in each assembly. In the training mode of operation information summed in each assembly is applied to a scalar multiplier and the resulting information is in turn applied to a threshold stage which is actuated to produce an output if the input applied thereto attains a prescribed value. Concurrently, the summed outputs of the junction elements are fed back to these elements to modify their transfer functions. The outputs of the threshold stages are finally processed for identification of the classes of events. In the training mode of operation the occurence of ambiguous and undesired identifications cause feedback to the pertinent scalar multipliers to decrease their multiplication factors. Such decreases are made until no further ambiguous and undesired identifications occur. At the completion of the training for a particular group of related classes of events, the values of the transfer functions of the junction elements as well as the multipliers have attained final desired values. Then, in the trained mode of operation for the separation and identification of the group of classes for which the system has been trained, the feedback to the junction elements, and the scalar multipliers with their feedback arrangements are not employed or are removed.

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