专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明授权

US06212508B1 Process and arrangement for conditioning an input variable of a neural network 失效
标题翻译：用于调节神经网络的输入变量的过程和布置
公开(公告)号：US06212508B1
公开(公告)日：2001-04-03
申请号：US08809210
申请日：1997-03-17
申请人： Volkmar Sterzing , Volker Tresp , Jörg Maschlanka
发明人： Volkmar Sterzing , Volker Tresp , Jörg Maschlanka
IPC分类号： G06N306
CPC分类号： G06K9/6298 , G06N3/049
摘要： A process and an arrangement for conditioning input variables of a neural network are described by the invention. From the input variables of the network, time series are formed and these are subdivided into intervals whose length depends on how far the interval and the measured variables contained therein lie back in the past. In this case, the interval length is selected to be larger the further the interval lies back in the past. By means of convolution using a bell-shaped function, a representative input value for the neural network is obtained from all these measured variables contained in the interval. All the input variables which are obtained in this way are fed to the network simultaneously during training and during operation. A memory is thus realized in a simple way for a forwardly directed neural network. Potential applications include, in particular, chemical processes having very different time constants.
摘要翻译：用于调节神经网络的输入变量的过程和布置由本发明描述。从网络的输入变量，形成时间序列，并将它们细分为间隔，其间隔取决于间隔和其中包含的测量变量在过去的距离。在这种情况下，间隔长度被选择为比过去更远。通过使用钟形函数的卷积，从包含在间隔中的所有这些测量变量获得神经网络的代表性输入值。所有以这种方式获得的输入变量在训练期间和运行期间同时馈送到网络。因此，以向前导向的神经网络的简单方式实现存储器。潜在的应用尤其包括具有非常不同时间常数的化学过程。

2. 发明授权

US06708160B1 Object nets 失效
标题翻译：对象网
公开(公告)号：US06708160B1
公开(公告)日：2004-03-16
申请号：US09544143
申请日：2000-04-06
申请人： Paul J. Werbos
发明人： Paul J. Werbos
IPC分类号： G06N306
CPC分类号： G06N3/02
摘要： A method, system and computer program product for implementing at least one of a learning-based diagnostics system and a control system (e.g., using a neural network). By using ObjectNets to model general object types, it is possible to design a control system that represents system components as relational structures rather than fixed vectors. Such an advance is possible by exploiting non-Euclidean principles of symmetry.
摘要翻译：一种用于实现基于学习的诊断系统和控制系统（例如，使用神经网络）中的至少一个的方法，系统和计算机程序产品。通过使用ObjectNets对一般对象类型进行建模，可以设计一个将系统组件表示为关系结构而不是固定向量的控制系统。通过开发非欧几里德的对称原则，这样的进步是可能的。

3. 发明授权

US06502083B1 Neuron architecture having a dual structure and neural networks incorporating the same 失效
标题翻译：具有双重结构的神经元结构和包含其的神经网络
公开(公告)号：US06502083B1
公开(公告)日：2002-12-31
申请号：US09470458
申请日：1999-12-22
申请人： Didier Louis , Pascal Tannhof , Andre Steimle
发明人： Didier Louis , Pascal Tannhof , Andre Steimle
IPC分类号： G06N306
CPC分类号： G06K9/6276 , G06N3/063
摘要： The improved neuron is connected to input buses which transport input data and control signals. It basically consists of a computation block, a register block, an evaluation block and a daisy chain block. All these blocks, except the computation block substantially have a symmetric construction. Registers are used to store data: the local norm and context, the distance, the AIF value and the category. The improved neuron further needs some R/W memory capacity which may be placed either in the neuron or outside. The evaluation circuit is connected to an output bus to generate global signals thereon. The daisy chain block allows to chain the improved neuron with others to form an artificial neural network (ANN). The improved neuron may work either as a single neuron (single mode) or as two independent neurons (dual mode). In the latter case, the computation block, which is common to the two dual neurons, must operate sequentially to service one neuron after the other. The selection between the two modes (single/dual) is made by the user which stores a specific logic value in a dedicated register of the control logic circuitry in each improved neuron.
摘要翻译：改进的神经元连接到传输输入数据和控制信号的输入总线。它基本上由计算块，寄存器块，评估块和菊花链块组成。除了计算块之外，所有这些块基本上具有对称结构。寄存器用于存储数据：本地规范和上下文，距离，AIF值和类别。改进的神经元还需要一些R / W记忆容量，这可能被放置在神经元或外部。评估电路连接到输出总线，以在其上产生全局信号。菊花链块允许与其他人链接改进的神经元以形成人造神经网络（ANN）。改善的神经元可以作为单个神经元（单个模式）或两个独立的神经元（双模式）起作用。在后一种情况下，两个双重神经元共同的计算块必须依次操作，以便在一个神经元之后进行服务。两种模式之间的选择（单/双）由在每个改进的神经元中的控制逻辑电路的专用寄存器中存储特定逻辑值的用户进行。

4. 发明授权

US06782375B2 Neural network based decision processor and method 有权
标题翻译：基于神经网络的决策处理器和方法
公开(公告)号：US06782375B2
公开(公告)日：2004-08-24
申请号：US09761328
申请日：2001-01-16
申请人： Eiman Abdel-Moneim , Anas Osman , Azhar M. Usman , Michael T. Mosier
发明人： Eiman Abdel-Moneim , Anas Osman , Azhar M. Usman , Michael T. Mosier
IPC分类号： G06N306
CPC分类号： G06N3/02
摘要： A computer network-based customer acquisition server and method of selecting preferred products includes using a neural network-based decision engine that automatically generate queries and select preferred products as a function of responses to the queries.
摘要翻译：基于计算机网络的客户获取服务器和选择优选产品的方法包括使用基于神经网络的决策引擎，其自动生成查询并且根据对查询的响应来选择优选产品。

5. 发明授权

US06496815B1 Neuron, hierarchical neural network using the neuron, and multiplying circuit used for multiplying process in the neuron 失效
标题翻译：神经元，使用神经元的分级神经网络，以及用于在神经元中乘法过程的乘法电路
公开(公告)号：US06496815B1
公开(公告)日：2002-12-17
申请号：US09577353
申请日：2000-05-24
申请人： Takeshi Kawashima
发明人： Takeshi Kawashima
IPC分类号： G06N306
CPC分类号： G06N3/049
摘要： There is provided a neuron which is capable of expressing an excitative coupling and a suppressive coupling by one signal by devising signals processed in the neuron to reduce a circuit area of a neural network in constructing the neural network by a digital electronic circuit. A multiplying block calculates a numerical value following a normal distribution N(wx, 1) by using a corresponding link weight w under the supposition that delay time of each pulse of an input signal follows a normal distribution of N(x, 1). Next, an adding block adds the numerical values calculated by the respective multiplying blocks one after another and a non-linear operating block counts a number of positive values within the added value obtained by the adding block. A pulse delaying block delays output pulse following a normal distribution in which delay time is 0 in average generated by a basic pulse generating block based on the result of operation of the non-linear operating block to output as an output signal.
摘要翻译：提供了一种神经元，其能够通过设计在神经元中处理的信号来表达一个信号的兴奋耦合和抑制耦合，以减少由数字电子电路构建神经网络的神经网络的电路面积。假设输入信号的每个脉冲的延迟时间遵循N（x，1）的正态分布，乘法块通过使用对应的链路权重w来计算正态分布N（wx，1）之后的数值。接下来，添加块将相应的各个乘法块计算出的数值相加，非线性运算块对由加法块获得的加法值中的正值的数量进行计数。脉冲延迟块基于正态分布延迟延迟输出脉冲，其中基于非线性运算块的运算结果，基本脉冲发生块产生的平均延迟时间为0，作为输出信号输出。

6. 发明授权

US06463424B1 Association unit, association apparatus and method for the same 失效
标题翻译：关联单位，关联设备及方法相同
公开(公告)号：US06463424B1
公开(公告)日：2002-10-08
申请号：US09064722
申请日：1998-04-23
申请人： Norio Ogata , Koji Ataka
发明人： Norio Ogata , Koji Ataka
IPC分类号： G06N306
CPC分类号： G06N3/04
摘要： There is provided a basic association unit for creating an information processing apparatus capable of performing information processing like information processing that actually occurs in central nerve systems of animals including human beings. The association unit is an unit for repeating input and output signals having m input terminals and n output terminals. When a first input signal which is a rectangular wave signal in the form of a pulse is simultaneously input to input terminals in a quantity less than m, an output signal having the same contents as the first input signal is output from particular output terminals which are associated with the input terminals in advance. When a third input signal is input to input terminals in a quantity less than m within a predetermined period of time after a second input signal is simultaneously input to input terminals in a quantity equal to or greater than m, an output signal having the same contents as that of the third input signal is output from all output terminals.
摘要翻译：提供了一种基本关联单元，用于创建能够执行类似信息处理的信息处理设备，该信息处理实际上发生在包括人类在内的动物的中枢神经系统中。关联单元是用于重复具有m个输入端子和n个输出端子的输入和输出信号的单元。当作为脉冲形式的矩形波信号的第一输入信号以小于m的量同时输入到输入端时，具有与第一输入信号相同内容的输出信号从特定输出端输出预先与输入端子相关联。当在第二输入信号同时输入到等于或大于m的数量的输入端子之后，在预定时间段内将第三输入信号以小于m的量输入到输入端时，具有相同内容的输出信号与第三输入信号的输出信号从所有输出端子输出。

7. 发明授权

US06622135B1 Method for detecting and classifying anomalies using artificial neural networks 有权
标题翻译：使用人工神经网络检测和分类异常的方法
公开(公告)号：US06622135B1
公开(公告)日：2003-09-16
申请号：US09465088
申请日：1999-12-16
申请人： Gislain Imbert De Tremiolles , Pascal Tannhof , Erin Williams
发明人： Gislain Imbert De Tremiolles , Pascal Tannhof , Erin Williams
IPC分类号： G06N306
CPC分类号： G06K9/6276 , G06T7/0004 , G06T2207/30148
摘要： To avoid the problem of category assignment in artificial neural networks (ANNs) based upon a mapping of the input space (like ROI and KNN algorithms), the present method uses “probabilities”. Now patterns memorized as prototypes do not represent categories any longer but the “probabilities” to belong to categories. Thus, after having memorized the most representative patterns in a first step of the learning phase, the second step consists of an evaluation of these probabilities. To that end, several counters are associated with each prototype and are used to evaluate the response frequency and accuracy for each neuron of the ANN. These counters are dynamically incremented during this second step using distances evaluation (between the input vectors and the prototypes) and error criteria (for example the differences between the desired responses and the response given by the ANN). At the end of the learning phase, a function of the contents of these counters allows an evaluation of these probabilities for each neuron to belong to predetermined categories. During the recognition phase, the probabilities associated with the neurons selected by the algorithm permit the characterization of new input vectors and more generally any kind of input (images, signals, sets of data) to detect and classify anomalies. The method allows a significant reduction in the number of neurons that are required in the ANN while improving its overall response accuracy.
摘要翻译：为了避免基于输入空间（如ROI和KNN算法）的映射的人造神经网络（ANN）中的类别分配问题，本方法使用“概率”。现在存储为原型的图案不再代表类别，而是属于类别的“概率”。因此，在学习阶段的第一步中记住最具代表性的模式之后，第二步包括这些概率的评估。为此，几个计数器与每个原型相关联，并用于评估ANN的每个神经元的响应频率和精度。这些计数器在第二步使用距离评估（输入向量和原型之间）和错误标准（例如期望响应与ANN给出的响应之间的差异）进行动态递增。在学习阶段结束时，这些计数器的内容的功能允许将每个神经元的这些概率的评估属于预定类别。在识别阶段，与算法选择的神经元相关联的概率允许表征新的输入向量，更一般地，可以检测和分类异常的任何种类的输入（图像，信号，数据集）。该方法允许在ANN中需要的神经元数目显着减少，同时提高其整体响应精度。

8. 发明授权

US06523018B1 Neural chip architecture and neural networks incorporated therein 失效
标题翻译：纳入其中的神经芯片架构和神经网络
公开(公告)号：US06523018B1
公开(公告)日：2003-02-18
申请号：US09470459
申请日：1999-12-22
申请人： Didier Louis , Pascal Tannhof , André Steimle
发明人： Didier Louis , Pascal Tannhof , André Steimle
IPC分类号： G06N306
CPC分类号： G06K9/6276 , G06N3/063
摘要： The neural semiconductor chip first includes: a global register and control logic circuit block, a R/W memory block and a plurality of neurons fed by buses transporting data such as the input vector data, set-up parameters, etc., and signals such as the feed back and control signals. The R/W memory block, typically a RAM, is common to all neurons to avoid circuit duplication, increasing thereby the number of neurons integrated in the chip. The R/W memory stores the prototype components. Each neuron comprises a computation block, a register block, an evaluation block and a daisy chain block to chain the neurons. All these blocks (except the computation block) have a symmetric structure and are designed so that each neuron may operate in a dual manner, i.e. either as a single neuron (single mode) or as two independent neurons (dual mode). Each neuron generates local signals. The neural chip further includes an OR circuit which performs an OR function for all corresponding local signals to generate global signals that are merged in an on-chip common communication bus shared by all neurons of the chip. The R/W memory block, the neurons and the OR circuit form an artificial neural network having high flexibility due to this dual mode feature which allows to mix single and dual neurons in the ANN.
摘要翻译：神经半导体芯片首先包括：全局寄存器和控制逻辑电路块，R / W存储器块和由传送诸如输入向量数据，建立参数等的数据的总线馈送的多个神经元，以及诸如作为反馈和控制信号。 R / W存储器块（通常为RAM）对于所有神经元是共同的，以避免电路重复，从而增加集成在芯片中的神经元的数量。 R / W存储器存储原型组件。每个神经元包括计算块，寄存器块，评估块和菊花链块以链接神经元。所有这些块（计算块除外）具有对称结构，并且被设计成使得每个神经元可以以双重方式操作，即作为单个神经元（单个模式）或两个独立神经元（双模式）操作。每个神经元产生本地信号。所述神经芯片还包括OR电路，其对所有相应的本地信号执行OR功能，以产生合并在由所述芯片的所有神经元共享的片上公共通信总线中的全局信号。 R / W存储器块，神经元和OR电路形成具有高灵活性的人造神经网络，由于这种双模式特征，其允许在ANN中混合单个和双重神经元。

9. 发明授权

US06272480B1 Method and arrangement for the neural modelling of a dynamic system with non-linear stochastic behavior 失效
标题翻译：具有非线性随机行为的动态系统神经建模的方法和布置
公开(公告)号：US06272480B1
公开(公告)日：2001-08-07
申请号：US09175068
申请日：1998-10-19
申请人： Volker Tresp , Thomas Briegel
发明人： Volker Tresp , Thomas Briegel
IPC分类号： G06N306
CPC分类号： G06N3/049
摘要： In a method and arrangement for the neural modelling of a dynamic system with non-linear stochastic behavior wherein only a few measured values of the influencing variable are available and the remaining values of the time series are modelled, a combination of a non-linear computerized recurrent neural predictive network and a linear error model are employed to produce a prediction with the application of maximum likelihood adaption rules. The computerized recurrent neural network can be trained with the assistance of the real-time recurrent learning rule, and the linear error model is trained with the assistance of the error model adaption rule that is implemented on the basis of forward-backward Kalman equations. This model is utilized in order to predict values of the glucose-insulin metabolism of a diabetes patient.
摘要翻译：在具有非线性随机行为的动态系统的神经建模的方法和装置中，其中仅影响变量的几个测量值可用并且时间序列的剩余值被建模，非线性计算机化循环神经预测网络和线性误差模型被用于通过应用最大似然适应规则来产生预测。计算机化循环神经网络可以在实时循环学习规则的帮助下进行训练，并在基于前向卡尔曼方程实现的误差模型适应规则的协助下训练线性误差模型。该模型用于预测糖尿病患者的葡萄糖 - 胰岛素代谢值。

10. 发明授权

US06625588B1 Associative neuron in an artificial neural network 有权
标题翻译：人工神经网络中的关联神经元
公开(公告)号：US06625588B1
公开(公告)日：2003-09-23
申请号：US09381825
申请日：1999-09-24
申请人： Pentti Haikonen
发明人： Pentti Haikonen
IPC分类号： G06N306
CPC分类号： G06N3/063
摘要： An associative artificial neuron and method of forming output signals of an associative artificial neuron includes receiving a number of auxiliary input signals; forming from the auxiliary input signals a sum weighted by coefficients and applying a non-linear function to the weighted sum to generate a non-linear signal. The neuron and method further include receiving a main input signal and forming, based on the main signal and the non-linear signal, the function S OR V, which is used to generate a main output signal, and at lest one of three logical functions S AND V, NOT S AND V, and S AND NOT V. The at least one logical function is used to generate an additional output signal for the associative artificial neuron.
摘要翻译：联想人造神经元和形成关联人造神经元的输出信号的方法包括接收多个辅助输入信号; 从辅助输入信号形成由系数加权的和并将非线性函数应用于加权和以产生非线性信号。神经元和方法还包括接收主输入信号，并且基于主信号和非线性信号形成用于产生主输出信号的功能S或V，以及至少三个逻辑功能中的一个 S和V，NOT S和V，以及S AND NOT V.所述至少一个逻辑功能用于产生关联人造神经元的附加输出信号。

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