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

US06363369B1 Dynamic synapse for signal processing in neural networks 失效
标题翻译：神经网络中信号处理的动态突触
公开(公告)号：US06363369B1
公开(公告)日：2002-03-26
申请号：US09096678
申请日：1998-06-11
申请人： Jim-Shih Liaw , Theodore W. Berger
发明人： Jim-Shih Liaw , Theodore W. Berger
IPC分类号： G06N304
CPC分类号： G06N3/049
摘要： An information processing system having signal processors that are interconnected by processing junctions that simulate and extend biological neural networks. Each processing junction receives signals from one signal processor and generates a new signal to another signal processor. The response of each processing junction is determined by internal junction processes and is continuously changed with temporal variation in the received signal. Different processing junctions connected to receive a common signal from a signal processor respond differently to produce different signals to downstream signal processors. This transforms a temporal pattern of a signal train of spikes into a spatio-temporal pattern of junction events and provides an exponential computational power to signal processors. Each signal processing junction can receive a feedback signal from a downstream signal processor so that an internal junction process can be adjusted to learn certain characteristics embedded in received signals.
摘要翻译：具有信号处理器的信息处理系统，其通过处理模拟和扩展生物神经网络的连接点相互连接。每个处理结从一个信号处理器接收信号，并向另一个信号处理器产生一个新信号。每个处理结的响应由内部连接处理确定，并且随着接收信号的时间变化而不断变化。连接以从信号处理器接收公共信号的不同处理结点响应不同，以向下行信号处理器产生不同的信号。这将尖峰的信号序列的时间模式转换成结事件的时空模式，并向信号处理器提供指数计算能力。每个信号处理结可以从下游信号处理器接收反馈信号，使得可以调整内部连接处理以学习嵌入在接收信号中的某些特性。

2. 发明授权

US06356884B1 Device system for the autonomous generation of useful information 有权
标题翻译：系统为自主生成有用的信息
公开(公告)号：US06356884B1
公开(公告)日：2002-03-12
申请号：US09347210
申请日：1999-07-02
申请人： Stephen L. Thaler
发明人： Stephen L. Thaler
IPC分类号： G06N304
CPC分类号： G06N3/04 , G06E1/00 , G06F15/18 , G06N3/0427
摘要： An artificial neural network-based system and method for determining desired concepts and relationships within a predefined field of endeavor, including a neural network portion, which neural network portion includes an artificial neural network that has been previously trained in accordance with a set of given training exemplars, a monitor portion associated with the neural network portion to observe the data outputs produced by the previously trained artificial neural network, and a perturbation portion for perturbing the neural network portion to effect changes, subject to design constraints of the artificial neural network that remain unperturbed, in the outputs produced by the neural network portion, the perturbation portion operable such that production of an output by the neural network portion thereafter effects a perturbation of the neural network portion by the perturbation portion, the monitor portion responsive to detection of the data outputs being produced by the previously trained neural network, whereby the system is operable to derive over a period of time a plurality of input/perturbation/output mapping relationships that differ from the input/perturbation/mapping relationships of the training exemplars.
摘要翻译：一种基于人造神经网络的系统和方法，用于在预定义的领域内确定期望的概念和关系，包括神经网络部分，所述神经网络部分包括先前已经根据一组给定训练训练的人造神经网络示例性地，与神经网络部分相关联的监视器部分以观察由先前训练的人造神经网络产生的数据输出，以及扰动部分，用于扰动神经网络部分以进行改变，受到保留的人造神经网络的设计约束在由神经网络部分产生的输出中，扰动部分可操作使得神经网络部分的输出的产生此后通过扰动部分实现神经网络部分的扰动，监视部分响应于数据的检测输出由前一个产生训练有素的神经网络，由此系统可操作地在一段时间内导出与训练样本的输入/扰动/映射关系不同的多个输入/扰动/输出映射关系。

3. 发明授权

US06336107B1 Method and system of automatic arrangement of composing elements 失效
标题翻译：组合元素自动排列的方法和系统
公开(公告)号：US06336107B1
公开(公告)日：2002-01-01
申请号：US09124890
申请日：1998-07-30
申请人： Tomohiro Uchida , Natsuki Oka , Hiroyuki Yoshimura
发明人： Tomohiro Uchida , Natsuki Oka , Hiroyuki Yoshimura
IPC分类号： G06N304
CPC分类号： G06F17/5072
摘要： past positions of a plurality of composing elements indicated by various past arrangement examples are given to each potential function corresponding to one composing element, and parameter values of the potential functions corresponding to the composing elements are automatically set on condition that a past total potential energy obtained by solving the potential functions is minimized. Thereafter, the parameter values are given to the potential functions in which a position of any composing element is not determined, and particular positions of the composing elements are determined on condition that a total potential energy obtained by solving the potential functions is minimized. Because each potential function corresponding to one composing element has an attraction term indicating the attraction between the composing element and the other composing elements and an attraction-repulsion term indicating the setting of the composing element at a position spaced at moderate distances from the other composing elements, the particular positions of the composing elements are set in an optimum arrangement. Accordingly, the optimum arrangement of the composing elements can be automatically obtained without extracting any arrangement knowledge from a skilled person.
摘要翻译：对于与一个构成要素相对应的各个电位函数，赋予由各种过去的配置例子指示的多个组成元素的过去位置，并且在获得的过去总势能的条件下自动设置与组成元素相对应的潜在函数的参数值通过解决潜在的功能最小化。此后，将参数值赋予未确定任何组成元素的位置的潜在功能，并且在通过求解潜在功能获得的总势能最小化的条件下确定组成元件的特定位置。由于与一个构成要素对应的每个潜在功能具有表示构成要素与其他构成要素之间的吸引力的吸引项，还具有表示构成要素在与其他构成要素间隔中距离的位置的设定的吸引力排斥项，组合元件的特定位置被设定为最佳布置。因此，可以自动获得组合元件的最佳布置，而不需要从技术人员那里提取任何安排知识。

4. 发明授权

US06456992B1 Semiconductor arithmetic circuit 失效
标题翻译：半导体运算电路
公开(公告)号：US06456992B1
公开(公告)日：2002-09-24
申请号：US08913680
申请日：1997-11-07
申请人： Tadashi Shibata , Tadahiro Ohmi , Tatsuo Morimoto , Ryu Kaiwara
发明人： Tadashi Shibata , Tadahiro Ohmi , Tatsuo Morimoto , Ryu Kaiwara
IPC分类号： G06N304
CPC分类号： G06N3/0635
摘要： A semiconductor arithmetic circuit which compares the magnitudes of a plurality of data with each other in real time by using a simple circuit. The semiconductor arithmetic circuit containing one or more neuron MOS transistors each having a plurality of input gate electrodes has an inverter circuit group of a plurality of inverter circuit each of which is constituted of neuron MOS transistors and a means for applying a prescribed signal voltage to at least one first input gate of the inverter circuit. The out put signals of all the inverters in the inverter circuit group, the output signal of a logical operation circuit generated by passing the output signals of the inverters through a multistage inverter circuit and inputting them into the logical operation circuit, or the output signal of a multistage inverter circuit generated by passing the output signal of the logical operation circuit through the multistage inverter circuit is fed back to at least one second input gate of the inverter circuit in the inverter circuit group.
摘要翻译：一种半导体运算电路，其通过使用简单电路实时地比较多个数据的大小。包含一个或多个具有多个输入栅电极的神经元MOS晶体管的半导体运算电路具有逆变器电路组多个反相器电路，每个反相器电路由神经元MOS晶体管构成，以及用于将规定的信号电压施加到逆变器电路的至少一个第一输入栅极的装置。逆变器电路组中的所有反相器的输出信号，通过使多级逆变器电路通过反相器的输出信号并将其输入逻辑运算电路而产生的逻辑运算电路的输出信号，或者输出信号通过将逻辑运算电路的输出信号通过多级逆变器电路而产生的多级逆变器电路被反馈到逆变器电路组中的逆变器电路的至少一个第二输入门。

5. 发明授权

US06345264B1 Methods and apparatus, using expansion attributes having default, values, for matching entities and predicting an attribute of an entity 失效
标题翻译：方法和装置，使用具有默认值的扩展属性，用于匹配实体和预测实体的属性
公开(公告)号：US06345264B1
公开(公告)日：2002-02-05
申请号：US09010819
申请日：1998-01-22
申请人： John S. Breese , Carl M. Kadie
发明人： John S. Breese , Carl M. Kadie
IPC分类号： G06N304
CPC分类号： G06F17/30867 , Y10S707/99933 , Y10S707/99935 , Y10S707/99936 , Y10S707/99945
摘要： Matching (e.g., via correlation or similarity process) entities having attributes, some of which have associated values. The values of the attributes may be adjusted based on number of entities that have values for a particular attribute so that the values decrease as the number increases. The attributes of the entities may be harmonized and provided with default values so that entities being matched have common attributes defined by the union of the attributes of the entities being matched. The attributes of the entities may be expanded and provided with default values so that the entities being matched have attributes that neither had originally. Match values may be normalized to provide a weight value which may be used to predict an attribute value of a new entity based on known attribute values of known entities. The weight values may be tuned such that relatively high weights are amplified and relatively low weights are suppressed.
摘要翻译：具有属性（例如，经由相关或相似性处理）匹配（其中一些具有相关联的值）。可以基于具有特定属性的值的实体的数量来调整属性的值，使得值随着数量的增加而减小。实体的属性可以被协调并且具有默认值，使得被匹配的实体具有由被匹配的实体的属性的并集定义的共同属性。可以扩展实体的属性并提供默认值，使得匹配的实体具有原始的属性。匹配值可以被归一化以提供可以用于基于已知实体的已知属性值来预测新实体的属性值的权重值。可以调整权重值，使得相对较高的权重被放大并且相对较低的权重被抑制。

6. 发明授权

US06336109B2 Method and apparatus for inducing rules from data classifiers 失效
标题翻译：从数据分类器诱导规则的方法和装置
公开(公告)号：US06336109B2
公开(公告)日：2002-01-01
申请号：US08840115
申请日：1997-04-15
申请人： Gary Howard
发明人： Gary Howard
IPC分类号： G06N304
CPC分类号： G06K9/626 , G06N3/0427 , G06N5/025 , G06N7/005
摘要： A method of processing data relating to a plurality of examples using a data classifier arranged to classify input data into one of a number of classes, and a rule inducer, comprising the steps of: (i) inputting a series of inputs to the data classifier so as to obtain a series of corresponding outputs; (ii) inputting said series of outputs and at least some of said series of inputs to the rule inducer so as to obtain a series of rules which describe relationships between the series of inputs to the data classifier and the series of corresponding outputs from the data classifier.
摘要翻译：一种使用布置成将输入数据分类为多个类别的规则诱导器的数据分类器来处理与多个示例相关的数据的方法，包括以下步骤：（i）将一系列输入输入到数据分类器以便获得一系列对应的输出;（ii）将所述一系列输出和所述一系列输入中的至少一些输入到规则诱导器，以便获得描述数据的一系列输入之间的关系的一系列规则分类器和数据分类器的一系列相应输出。

7. 发明授权

US06643627B2 Dynamic synapse for signal processing in neural networks 有权
公开(公告)号：US06643627B2
公开(公告)日：2003-11-04
申请号：US10108199
申请日：2002-03-26
申请人： Jim-Shih Liaw , Theodore W. Berger
发明人： Jim-Shih Liaw , Theodore W. Berger
IPC分类号： G06N304
CPC分类号： G06N3/049
摘要： An information processing system having signal processors that are interconnected by processing junctions that simulate and extend biological neural networks. Each processing junction receives signals from one signal processor and generates a new signal to another signal processor. The response of each processing junction is determined by internal junction processes and is continuously changed with temporal variation in the received signal. Different processing junctions connected to receive a common signal from a signal processor respond differently to produce different signals to downstream signal processors. This transforms a temporal pattern of a signal train of spikes into a spatio-temporal pattern of junction events and provides an exponential computational power to signal processors. Each signal processing junction can receive a feedback signal from a downstream signal processor so that an internal junction process can be adjusted to learn certain characteristics embedded in received signals.

8. 发明授权

US06581048B1 3-brain architecture for an intelligent decision and control system 失效
标题翻译：智能决策和控制系统的3脑架构
公开(公告)号：US06581048B1
公开(公告)日：2003-06-17
申请号：US09147338
申请日：1999-05-10
申请人： Paul J. Werbos
发明人： Paul J. Werbos
IPC分类号： G06N304
CPC分类号： G05B13/0285 , G05B13/0265 , G05B13/027 , G06N3/105
摘要： A method and system for intelligent control of external devices using a mammalian brain-like structure having three parts. The method and system include a computer-implemented neural network system which is an extension of the model-based adaptive critic design and is applicable to real-time control (e.g., robotic control) and real-time distributed control. Additional uses include data visualization, data mining, and other tasks requiring complex analysis of inter-relationships between data.
摘要翻译：使用具有三部分的哺乳动物脑样结构来对外部设备进行智能控制的方法和系统。该方法和系统包括计算机实现的神经网络系统，其是基于模型的自适应评估器设计的扩展，并且可应用于实时控制（例如，机器人控制）和实时分布式控制。其他用途包括数据可视化，数据挖掘和其他需要复杂分析数据之间相互关系的任务。

9. 发明授权

US06456994B1 Computer for a quantum computer 失效
标题翻译：量子计算机的编译器
公开(公告)号：US06456994B1
公开(公告)日：2002-09-24
申请号：US09073132
申请日：1998-05-05
申请人： Robert Tucci
发明人： Robert Tucci
IPC分类号： G06N304
CPC分类号： G06N99/002 , B82Y10/00 , G06N7/005 , Y10S977/933
摘要： A quantum computer is an array of quantum hits (qubits) together with some hard-ware for manipulating these qubits. Quantum Bayesian (QB) nets are a method of modeling quantum systems graphically in terms of network diagrams. This invention comprises a classical computer running a Computer program that expresses the information contained in a QB net as a sequence of elementary operations (SEO). One can then run these sequences on a quantum computer. We show how to reduce a QB net into a SEO by a two step process. First, express the information contained in the QB net as a sequence of unitary operators. Second, express each of those unitary operators as a SEO. An appendix to this document contains the C++ source code of a computer program called “Qubiter1.0”, which is a preferred embodiment of the invention.
摘要翻译：量子计算机是量子命中（量子位）的阵列，以及用于操纵这些量子位的一些硬件。量子贝叶斯（QB）网络是以图形方式对网络图进行量子系统建模的方法。本发明包括运行计算机程序的经典计算机，其将包含在QB网络中的信息表示为基本操作（SEO）序列。然后可以在量子计算机上运行这些序列。我们展示了如何通过两步过程将QB网络减少到SEO。首先，将QB网络中包含的信息作为单一运算符序列表示。第二，将这些单一运营商的每一个表达为SEO。本文档的附录包含称为“Qubiter1.0”的计算机程序的C ++源代码，这是本发明的优选实施例。

10. 发明授权

US06411946B1 Route optimization and traffic management in an ATM network using neural computing 有权
标题翻译：使用神经计算的ATM网络中的路由优化和流量管理
公开(公告)号：US06411946B1
公开(公告)日：2002-06-25
申请号：US09143687
申请日：1998-08-28
申请人： Aloke Chaudhuri
发明人： Aloke Chaudhuri
IPC分类号： G06N304
CPC分类号： H04L43/16 , G06Q20/102 , H04L41/147 , H04L41/16 , H04L45/08
摘要： Neural computing techniques are used to optimize route selection in a communication network, such as an ATM network. Output measurements of the network are used to provide optimal routing selection and traffic management. Specifically, link data traffic is monitored in the network to obtain traffic history data. An autoregressive backpropagation neural network is trained using the traffic history data to obtain respective predicted traffic profiles for the links. Particular links are then selected for carrying data based on the predicted traffic profiles. A cost function, limits on network parameters such as link cost and cell rate, and other quality of service factors are also considered in selecting the optimal route.
摘要翻译：神经计算技术用于优化诸如ATM网络之类的通信网络中的路由选择。网络的输出测量用于提供最佳路由选择和流量管理。具体来说，在网络中监视链路数据流量，以获得流量历史数据。使用交通历史数据训练自回归反向传播神经网络，以获得链路的相应预测的业务量。然后选择特定的链接以基于预测的流量简档来承载数据。在选择最优路由时，还考虑了成本函数，对网络参数（如链路成本和信元速率）以及其他服务质量因素的限制。

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