-
1.发明授权Method and apparatus for computer-supported generation of at least one artificial training data vector for a neural network 失效用于计算机支持的用于神经网络的至少一个人造训练数据矢量生成的方法和装置公开(公告)号：US06282529B1
公开(公告)日：2001-08-28
申请号：US09254298
申请日：1999-03-03
IPC分类号： G06N302
摘要： A method and apparatus for computer-supported generation of at least one artificial training data vector for a neural network is provided wherein a residual error is determined after a training of a neural network has occurred. A backward error is then determined from the residual error. Artificial training data vectors are generated from a statistical random process that is based on a statistical distribution, such that the respective backward error for an input of the neural network is taken into consideration.
摘要翻译： 提供了一种用于计算机支持地生成用于神经网络的人造训练数据向量的方法和装置，其中在发生神经网络的训练之后确定残差。 然后从剩余误差确定后向误差。 从基于统计分布的统计随机过程生成人造训练数据向量，使得考虑到神经网络的输入的相应的后向误差。
-
公开(公告)号：US06317730B1
公开(公告)日：2001-11-13
申请号：US09194263
申请日：1998-11-23
IPC分类号： G06F1518
CPC分类号： G06N3/0436 , G06N7/046
摘要： A set of fuzzy rules (FR) is mapped onto a neural network (NN) (501). The neural network (NN) is trained (502), and weights (wi) and/or neurons (NE) of the neural network (NN) are pruned or grown (503). A new neural network (NNN) formed in this way is mapped onto a new fuzzy rule set (NFR) (504).
摘要翻译： 一组模糊规则（FR）被映射到神经网络（NN）（501）上。 神经网络（NN）被训练（502），神经网络（NN）的权重（wi）和/或神经元（NE）被修剪或生长（503）。 以这种方式形成的新神经网络（NNN）映射到新的模糊规则集（NFR）（504）。
-
3.发明授权ASSEMBLY OF INTERCONNECTED COMPUTING ELEMENTS, METHOD FOR COMPUTER-ASSISTED DETERMINATION OF A DYNAMICS WHICH IS THE BASE OF A DYNAMIC PROCESS, AND METHOD FOR COMPUTER-ASSISTED TRAINING OF AN ASSEMBLY OF INTERCONNECTED ELEMENTS 失效互连计算单元的组合，用于计算机辅助确定作为动态过程基础的动力学的方法以及用于计算机辅助训练组合互连元件的方法公开(公告)号：US06493691B1
公开(公告)日：2002-12-10
申请号：US09529195
申请日：2000-04-07
IPC分类号： G06N302
CPC分类号： G06N3/049
摘要： An input signal is transformed into a predetermined space. Transformation computer elements are connected to one another such that transformed signals can be taken at the transformation computer elements, whereby at least three transformed signals relate to respectively successive points in time. Composite computer elements are respectively connected to two transformation computer elements. Further, a first output computer element is provided at which an output signal that describes a system status at a point in time can be taken. The first output computer element is connected to the transformation computer elements. Further, a second output computer element is provided that is connected to the composite computer elements and given whose employment a predetermined condition can be taken into consideration when training the arrangement.
摘要翻译： 输入信号被转换成预定的空间。 变换计算机元件彼此连接，使得转换的信号可以在转换计算机元件处获取，由此至少三个变换的信号分别与时间上相连。 复合计算机元件分别连接到两个转换计算机元件。 此外，提供第一输出计算机元件，在该第一输出计算机元件处可以采用描述在某个时间点的系统状态的输出信号。 第一个输出计算机元件连接到转换计算机元件。 此外，提供第二输出计算机元件，其连接到复合计算机元件并给予其在训练该布置时可以考虑使用预定条件。
-
4.发明授权System and method for training and using interconnected computation elements to determine a dynamic response on which a dynamic process is based 失效用于训练和使用互连的计算元素以确定基于动态过程的动态响应的系统和方法公开(公告)号：US06728691B1
公开(公告)日：2004-04-27
申请号：US09914850
申请日：2001-09-04
IPC分类号： G06F1518
CPC分类号： G06N3/049
摘要： Computation elements are connected to one another with a first subsystem having a first input computation element, to which time series values, which each describe one state of a system in a first state space at a time, can be supplied. The first input computation element is connected to a first intermediate computation element, by which a state of the system can be described in a second state space at a time. In a second subsystem a second intermediate computation element, by which a state of the system can be described in the second state space at a time, is connected to a first output computation element, on which a first output signal can be tapped off. In a third subsystem a third intermediate computation element, by which a state of the system can be described in the second state space at a time, is connected to a second output computation element, on which a second output signal can be tapped off. The first subsystem, the second subsystem and the third subsystem are each connected to one another by a coupling between the intermediate computation elements. Weights, which are each associated with one connection between two intermediate computation elements are equal to one another, and weights which are each associated with a connection between an intermediate computation element and an output computation element are equal to one another.
摘要翻译： 计算元件通过具有第一输入计算元件的第一子系统相互连接，每个时间序列值描述一次在第一状态空间中的系统的一个状态。 第一输入计算元件连接到第一中间计算元件，通过该第一中间计算元件，可以一次在第二状态空间中描述系统的状态。 在第二子系统中，通过该第二中间计算元件连接到第一输出计算元件，第一中间计算元件可以一次在第二状态空间中描述系统的状态，第一输出计算元件可以在其上分离第一输出信号。 在第三子系统中，第三中间计算元件连接到第二输出计算元件，第二中间计算元件可以在第二输出计算元件上将第二输出信号分配给该第二中间计算元件。 第一子系统，第二子系统和第三子系统各自通过中间计算元件之间的耦合彼此连接。 每个与两个中间计算元件之间的一个连接相关联的权重彼此相等，并且每个与中间计算元件和输出计算元件之间的连接相关联的权重彼此相等。
-
公开(公告)号：US20150134311A1
公开(公告)日：2015-05-14
申请号：US14075946
申请日：2013-11-08
IPC分类号： G06F19/00
摘要： Modeling effectiveness of a verum includes dividing a group of patients into a placebo group and a verum group, defining a plurality of characteristics of the group of patients, and generating a model for the placebo group based on the plurality of characteristics. The method also includes generating a model for the verum group based on the plurality of characteristics, and isolating a placebo effect in the verum group in order to determine a pure verum effect.
摘要翻译： 正确的建模功能包括将一组患者分成安慰剂组和正常组，定义患者组的多个特征，并且基于多个特征生成安慰剂组的模型。 该方法还包括基于多个特征为verum组生成模型，并且在verum组中分离安慰剂效应以便确定纯verum效应。
-
6.发明授权
公开(公告)号：US3942569A
公开(公告)日：1976-03-09
申请号：US528838
申请日：1974-12-02
CPC分类号： A22C13/0009 , Y10S206/802
摘要： This invention relates to a unilaterally closed cylindrical hollow stick of shirred tubular casing having a closure within the stick bore in the zone of the stick beginning and formed from the casing end itself, said closure being composed of a U-shaped body of longitudinally shirred tubular casing. The invention also relates to a process for the production of the closure.
摘要翻译： 本发明涉及一种单侧封闭的筒状筒状空心棒，其具有在该杆的区域内的该棒状孔内的封闭件，其从该壳体端部本身开始形成，该封闭件由纵向皱缩管状的U形体 套管。 本发明还涉及一种用于生产封闭件的方法。
-
7.发明授权Method for determination of weights, suitable for elimination, of a neural network using a computer 有权使用计算机确定适合于消除神经网络的权重的方法公开(公告)号：US06311172B1
公开(公告)日：2001-10-30
申请号：US09155197
申请日：1998-09-23
IPC分类号： G06F1518
CPC分类号： G06N3/08
摘要： The training phase of a neural network NN is stopped before an error function, which is to be minimized in the training phase, reaches a minimum (301). A first variable (EG) is defined using, for example, the optimal brain damage method or the optimal brain surgeon method, on the assumption that the error function is at the minimum. Furthermore, a second variable (ZG) is determined which provides an indication of the manner in which the value of the error function varies when a weight (wi) is removed from the neural network (NN). The first variable (EG) and the second variable (ZG) are used to classify the weight (wi) as being suitable or unsuitable for removal from the neural network (NN).
摘要翻译： 在训练阶段要最小化的误差函数达到最小（301）之前，停止神经网络NN的训练阶段。 假设误差函数为最小，使用例如最佳脑损伤方法或最佳脑外科医生方法来定义第一变量（EG）。 此外，确定第二变量（ZG），当从神经网络（NN）移除权重（wi）时，提供误差函数的值变化的方式的指示。 第一变量（EG）和第二变量（ZG）用于将权重（wi）分类为适合于或不适合于从神经网络（NN）中移除。
-
8.发明授权Method for the computer-aided learning of a recurrent neural network for modeling a dynamic system 有权用于建模动态系统的循环神经网络的计算机辅助学习方法公开(公告)号：US09235800B2
公开(公告)日：2016-01-12
申请号：US13640543
申请日：2011-04-12
IPC分类号： G06N3/08
CPC分类号： G06N3/08
摘要： A method for the computer-aided learning of a recurrent neural network for modeling a dynamic system which is characterized at respective times by an observable vector with one or more observables as entries is provided. The neural network includes both a causal network with a flow of information that is directed forwards in time and a retro-causal network with a flow of information which is directed backwards in time. The states of the dynamic system are characterized by first state vectors in the causal network and by second state vectors in the retro-causal network, wherein the state vectors each contain observables for the dynamic system and also hidden states of the dynamic system. Both networks are linked to one another by a combination of the observables from the relevant first and second state vectors and are learned on the basis of training date including known observables vectors.
摘要翻译： 提供了一种用于对动态系统进行建模的循环神经网络的计算机辅助学习的方法，该动态系统在各自的时间由具有一个或多个可观察值的可观察向量表征为条目。 神经网络包括具有时间向前指向的信息流的因果网络和具有时间向后指向的信息流的复原因果网络。 动态系统的状态由因果网络中的第一状态向量和复原因果网络中的第二状态向量表征，其中状态向量每个都包含动态系统的可观察值，以及动态系统的隐藏状态。 两个网络通过相关的第一和第二状态向量的可观察的组合彼此相关联，并且基于包括已知的可观察向量的训练日期来学习。
-
9.发明授权Method for the computer-assisted control and/or regulation of a technical system where the dynamic behavior of the technical system is modeled using a recurrent neural network 失效计算机辅助控制和/或调节技术系统的方法，其中技术系统的动态行为使用循环神经网络进行建模公开(公告)号：US08554707B2
公开(公告)日：2013-10-08
申请号：US12522040
申请日：2007-12-19
CPC分类号： G05B13/027 , G05B2219/33011 , G05B2219/33021 , G05B2219/33025 , G05B2219/33036 , G06N3/02
摘要： A method for the computer-assisted control and/or regulation of a technical system is provided. The method includes two steps, namely modeling the dynamic behavior of the technical system with a recurrent neural network using training data, the recurrent neural network includes states and actions determined using a simulation model at different times and learning an action selection rule by the recurrent neural network to a further neural network. The method can be used with any technical system in order to control the system in an optimum computer-assisted manner. For example, the method can be used in the control of a gas turbine.
摘要翻译： 提供了一种用于计算机辅助控制和/或调节技术系统的方法。 该方法包括两个步骤，即使用训练数据对具有循环神经网络的技术系统的动态行为进行建模，循环神经网络包括使用不同时间的模拟模型确定的状态和动作，并通过反复神经学习动作选择规则 网络进一步的神经网络。 该方法可以与任何技术系统一起使用，以便以最佳的计算机辅助方式控制系统。 例如，该方法可用于燃气轮机的控制。
-
10.发明申请METHOD FOR THE COMPUTER-AIDED LEARNING OF A RECURRENT NEURAL NETWORK FOR MODELING A DYNAMIC SYSTEM 有权用于建模动态系统的复现神经网络的计算机辅助学习方法公开(公告)号：US20130204815A1
公开(公告)日：2013-08-08
申请号：US13640543
申请日：2011-04-12
IPC分类号： G06N3/08
CPC分类号： G06N3/08
摘要： A method for the computer-aided learning of a recurrent neural network for modeling a dynamic system which is characterized at respective times by an observable vector with one or more observables as entries is provided. The neural network includes both a causal network with a flow of information that is directed forwards in time and a retro-causal network with a flow of information which is directed backwards in time. The states of the dynamic system are characterized by first state vectors in the causal network and by second state vectors in the retro-causal network, wherein the state vectors each contain observables for the dynamic system and also hidden states of the dynamic system. Both networks are linked to one another by a combination of the observables from the relevant first and second state vectors and are learned on the basis of training date including known observables vectors.
摘要翻译： 提供了一种用于对动态系统进行建模的循环神经网络的计算机辅助学习的方法，该动态系统在各自的时间由具有一个或多个可观察值的可观察向量表征为条目。 神经网络包括具有时间向前指向的信息流的因果网络和具有时间向后指向的信息流的复原因果网络。 动态系统的状态由因果网络中的第一状态向量和复原因果网络中的第二状态向量表征，其中状态向量每个都包含动态系统的可观察值，以及动态系统的隐藏状态。 两个网络通过相关的第一和第二状态向量的可观察的组合彼此相关联，并且基于包括已知的可观察向量的训练日期来学习。
-
-
-
-
-
-
-
-
-
搜索结果
18 条记录 (耗时 0.019 秒)
