公开(公告)号：US20040267682A1

公开(公告)日：2004-12-30

申请号：US10488927

申请日：2004-08-18

Inventor： Henrik Baur ,  Helmuth Eggers ,  Lars Kruger ,  Rainer Ott

IPC: G06E001/00 ,  G06E003/00 ,  G06G007/00 ,  G06F015/18

CPC classification number: G06K9/325

Abstract: A method for at least one of model-based classification and target recognition of an object. The method further includes recording an image of an object and determining a feature that represents a part of the object. Moreover, the method includes determining at least one condition associated with the feature that indicates an applicability of the feature based on at least one of: covering by parts of the object, a current illumination situation, time the image is recorded, movement information of the object, movement information of other objects, and a position and orientation of the object. The instant abstract is neither intended to define the invention disclosed in this specification nor intended to limit the scope of the invention in any way.

Abstract translation: 一种用于对象的基于模型的分类和目标识别中的至少一种的方法。 该方法还包括记录对象的图像并确定表示对象的一部分的特征。 此外，该方法包括基于以下至少一个来确定与特征相关联的至少一个条件，该条件指示该特征的适用性：覆盖对象的部分，当前照明情况，记录图像的时间， 对象，其他对象的运动信息以及对象的位置和方向。 本摘要既不旨在限定本说明书中公开的发明，也不旨在以任何方式限制本发明的范围。

公开(公告)号：US20040236708A1

公开(公告)日：2004-11-25

申请号：US10753013

申请日：2004-01-07

Applicant: CRANIAL TECHNOLOGIES, INC.

Inventor： Timothy R. Littlefield ,  Jeanne K. Pomatto

IPC: G06E001/00 ,  G06E003/00 ,  G06G007/00 ,  G06F015/18

CPC classification number: G06T1/0007 ,  B33Y50/00 ,  B33Y80/00 ,  G06N3/02 ,  G06T7/50 ,  G06T17/10 ,  G06T2207/30004 ,  G06T2210/41

Abstract: Databases and a system for operating on such databases are described in which data representative of first head shapes and corresponding modified head shapes and corresponding cranial remodeling devices are provided.

Abstract translation: 描述了用于在这样的数据库上操作的数据库和系统，其中提供了表示第一头部形状和对应的修改的头部形状的数据以及相应的头部重塑装置。

公开(公告)号：US20040193558A1

公开(公告)日：2004-09-30

申请号：US10730708

申请日：2003-12-08

Inventor： Alex Nugent

IPC: G06N003/08 ,  G06F015/18 ,  G06G007/00 ,  G06N003/02 ,  G06E003/00 ,  G06E001/00

CPC classification number: G06N3/063

Abstract: Methods and systems for modifying at least one synapse of a physical neural network. A physical neural network implemented as an adaptive neural network can be provided, which includes one or more neurons and one or more synapses thereof, wherein the neurons and synapses are formed from a plurality of nanoparticles disposed within a dielectric solution in association with one or more pre-synaptic electrodes and one or more post-synaptic electrodes and an applied electric field. At least one pulse can be generated from one or more of the neurons to one or more of the pre-synaptic electrodes of a succeeding neuron and one or more post-synaptic electrodes of one or more of the neurons of the physical neural network, thereby strengthening at least one nanoparticle of a plurality of nanoparticles disposed within the dielectric solution and at least one synapse thereof.

Abstract translation: 修改物理神经网络的至少一个突触的方法和系统。 可以提供实现为自适应神经网络的物理神经网络，其包括一个或多个神经元和一个或多个突触，其中所述神经元和突触由布置在电介质溶液内的多个纳米颗粒形成，所述多个纳米颗粒与一个或多个 突触前电极和一个或多个突触后电极和施加的电场。 至少一个脉冲可以从一个或多个神经元产生到物理神经网络的一个或多个神经元的后续神经元和一个或多个突触后电极的一个或多个突触前电极，由此 加强设置在电介质溶液内的多个纳米颗粒的至少一个纳米颗粒和至少一个突触。

公开(公告)号：US20040193386A1

公开(公告)日：2004-09-30

申请号：US10779365

申请日：2004-02-13

Inventor： Timothy D. Flynn ,  Robert Alan Hess ,  Barbara Noble

IPC: G06E001/00 ,  G06E003/00 ,  G06G007/00 ,  G06F015/18 ,  G01G007/00 ,  G01G009/00 ,  G01G011/00 ,  G06F015/00 ,  G06F015/02 ,  G01G017/00 ,  G01G019/00

CPC classification number: G06F17/17 ,  G01G19/07 ,  G06F17/175

Abstract: Described are systems and methods for determining the gross weight of an aircraft. A flight regime is determined based on one or more inputs. A neural net is selected based on a flight regime. The neural net inputs may include derived values. A first estimate of the gross weight is produced by the selected neural net. The first estimate is used, along with other inputs, with a Kalman filter to produce a final gross weight estimate. The Kalman filter blends or fuses together its inputs to produce the final gross weight estimate.

Abstract translation: 描述了用于确定飞行器总重量的系统和方法。 基于一个或多个输入确定飞行状态。 基于飞行状态选择神经网络。 神经网络输入可以包括派生值。 毛重的第一个估计是由选定的神经网络产生的。 第一个估计与其他输入一起用卡尔曼滤波器来产生最终总体估计。 卡尔曼滤波器将其输入共同融合或融合，以产生最终毛重估计。

公开(公告)号：US20040162795A1

公开(公告)日：2004-08-19

申请号：US10747381

申请日：2003-12-29

Inventor： Jesse Dougherty ,  David Ascher

IPC: G06E001/00 ,  G06E003/00 ,  G06G007/00 ,  G06F015/18

CPC classification number: G06Q10/107 ,  G06F16/353 ,  H04L51/12

Abstract: Certain embodiments provide a method and system for dynamic classification of incoming electronic messages in a communication system which includes formulating classification rules for classifying electronic messages according to criteria, extracting feature information from outgoing messages, modifying the classification rules based on the feature information extracted from outgoing messages, and analyzing an incoming message according to the classification rules. The extracting step may also include creating copies of the outgoing messages and extracting feature information from the copies of the outgoing messages. The method may further include classifying the incoming message according to the classification rules. The method may also include routing the incoming message to a destination based on the classification rules.

Abstract translation: 某些实施例提供了一种用于在通信系统中进入电子消息的动态分类的方法和系统，其包括根据标准制定用于对电子消息进行分类的分类规则，从传出消息中提取特征信息，基于从传出中提取的特征信息修改分类规则 消息，并根据分类规则分析传入消息。 提取步骤还可以包括创建出站消息的副本并从出局消息的副本中提取特征信息。 该方法还可以包括根据分类规则对输入消息进行分类。 该方法还可以包括基于分类规则将传入消息路由到目的地。

公开(公告)号：US20040148265A1

公开(公告)日：2004-07-29

申请号：US10752259

申请日：2004-01-06

Inventor： Steven D. Schwartz ,  Vern L. Schramm ,  Benjamin B. Braunheim

IPC: G01N031/00 ,  G06F019/00 ,  G06F015/18 ,  G06G007/00 ,  G06E003/00 ,  G06E001/00

CPC classification number: G06F19/16 ,  Y10S128/925 ,  Y10S706/924

Abstract: A new method to analyze and predict the binding energy for enzyme-transition state inhibitor interactions is presented. Computational neural networks are employed to discovery quantum mechanical features of transition states and putative inhibitors necessary for binding. The method is able to generate its own relationship between the quantum mechanical structure of the inhibitor and the strength of binding. Feed-forward neural networks with back propagation of error can be trained to recognize the quantum mechanical electrostatic potential at the entire van der Waals surface, rather than a collapsed representation, of a group of training inhibitors and to predict the strength of interactions between the enzyme and a group of novel inhibitors. The experimental results show that the neural networks can predict with quantitative accuracy the binding strength of new inhibitors. The method is in fact able to predict the large binding free energy of the transition state, when trained with less tightly bound inhibitors. The present method is also applicable to prediction of the binding free energy of a ligand to a receptor. The application of this approach to the study of transition state inhibitors and ligands would permit evaluation of chemical libraries of potential inhibitory, agonistic, or antagonistic agents. The method is amenable to incorporation in a computer-readable medium accessible by general-purpose computers.

Abstract translation: 提出了一种分析和预测酶 - 过渡态抑制剂相互作用的结合能的新方法。 计算神经网络用于发现过渡态的量子力学特征和结合所必需的推定的抑制因子。 该方法能够在抑制剂的量子力学结构与结合强度之间产生自己的关系。 可以训练具有误差反向传播的前馈神经网络，以识别整个范德瓦尔斯表面的量子力学静电势，而不是一组训练抑制剂的折叠表示，并预测酶之间的相互作用强度 和一组新的抑制剂。 实验结果表明，神经网络可以定量准确预测新型抑制剂的结合强度。 当用较不紧密结合的抑制剂进行训练时，该方法实际上能够预测过渡态的大的结合自由能。 本方法也适用于预测配体与受体的结合自由能。 这种方法应用于过渡态抑制剂和配体的研究将允许评估潜在的抑制性，激动剂或拮抗剂的化学文库。 该方法适于并入通用计算机可访问的计算机可读介质中。

公开(公告)号：US20040143561A1

公开(公告)日：2004-07-22

申请号：US10702517

申请日：2003-11-07

Inventor： Finn Verner Jensen ,  Helge Langseth

IPC: G06F017/00 ,  G06N005/02 ,  G06F015/18 ,  G06G007/00 ,  G06N003/02 ,  G06E003/00 ,  G06E001/00

CPC classification number: G06N7/005 ,  G06N5/02 ,  G06N20/00

Abstract: The invention pertains to a computer system for automated problem solving in technical systems with redundant components that via a user interface allows a skilled user to model the technical system and its components by using probabilities for causes, indications of redundant causes, probabilities that solutions repair causes, and the effects of questions on cause probabilities, and that via another user interface provides an end user with problem solving guidance by suggesting a sequence of questions and solutions, continually responded to by the user, until the failing system is repaired or all relevant solutions have been tried. The invention permits problem solving within industries where redundant components are often used to increase the safety of the system.

Abstract translation: 本发明涉及一种用于在具有冗余部件的技术系统中自动化问题解决的计算机系统，所述冗余部件经由用户界面允许技术用户通过使用原因的概率，冗余原因的指示，解决方案修复的概率来对技术系统及其部件进行建模 ，以及问题对原因概率的影响，以及通过另一个用户界面为最终用户提供问题解决指导，通过建议一系列问题和解决方案，由用户不断响应，直到故障系统被修复或所有相关解决方案 已经尝试过 本发明允许在通常使用冗余部件来增加系统的安全性的行业内解决问题。

公开(公告)号：US20040143559A1

公开(公告)日：2004-07-22

申请号：US10755946

申请日：2004-01-13

Inventor： Francisco J. Ayala

IPC: G06F001/30 ,  G06F001/28 ,  G06G007/00 ,  G06N003/00 ,  G06N003/12 ,  G06F015/18 ,  G06E001/00 ,  G06E003/00 ,  G06F001/26

CPC classification number: G05B13/0265 ,  G06N3/086

Abstract: In a method and system for developing a neural system adapted to perform a specified task, a population of neural systems is selected, each neural system comprising an array of interconnected neurons, and each neural system is encoded into a representative genome. For a given genome, a processing gene encodes a neural output function for each neuron, and the connections from each neuron are encoded by one or more connection genes, each connection gene including a weight function. The given neural system is operated to perform the specified task during a trial period, and performance is continually monitored during the trial period. Reinforcement signals determined from the continually monitored performance are applied as inputs to the functions respectively associated with each of the processing genes and connection genes of the given neural system. At the conclusion of the trial period, the fitness of the given neural system for performing the specified task is determined, usefully as a function of the reinforcement signals applied during the trial period. A set of genomes, respectively representing the neural systems of the population that have been determined to have the highest fitness values, are selected for use in forming a new generation of neural systems.

Abstract translation: 在用于开发适于执行指定任务的神经系统的方法和系统中，选择神经系统群体，每个神经系统包括相互联系的神经元的阵列，并且将每个神经系统编码为代表性基因组。 对于给定的基因组，处理基因编码每个神经元的神经输出函数，并且每个神经元的连接由一个或多个连接基因编码，每个连接基因包括权重函数。 给定的神经系统在试用期间进行指定的任务，并在试用期间持续监测性能。 从连续监测的性能确定的增强信号被用作分别与给定神经系统的处理基因和连接基因相关联的功能的输入。 在试用期结束时，确定用于执行指定任务的给定神经系统的适应度，作为在试用期间应用的加强信号的函数。 选择分别表示已经被确定为具有最佳适应度值的群体的神经系统的一组基因组用于形成新一代神经系统。

公开(公告)号：US20040133533A1

公开(公告)日：2004-07-08

申请号：US10614335

申请日：2003-07-07

Inventor： James David Keeler ,  Eric Jon Hartman ,  Ralph Bruce Ferguson

IPC: G06F017/00 ,  G06N005/02 ,  G06F015/18 ,  G06G007/00 ,  G06E003/00 ,  G06E001/00

CPC classification number: G06N3/049 ,  G06N3/0472

Abstract: A neural network system is provided that models the system in a system model (12) with the output thereof providing a predicted output. This predicted output is modified or controlled by an output control (14). Input data is processed in a data preprocess step (10) to reconcile the data for input to the system model (12). Additionally, the error resulted from the reconciliation is input to an uncertainty model to predict the uncertainty in the predicted output. This is input to a decision processor (20) which is utilized to control the output control (14). The output control (14) is controlled to either vary the predicted output or to inhibit the predicted output whenever the output of the uncertainty model (18) exceeds a predetermined decision threshold, input by a decision threshold block (22). Additionally, a validity model (16) is also provided which represents the reliability or validity of the output as a function of the number of data points in a given data region during training of the system model (12). This predicts the confidence in the predicted output which is also input to the decision processor (20). The decision processor (20) therefore bases its decision on the predicted confidence and the predicted uncertainty. Additionally, the uncertainty output by the data preprocess block (10) can be utilized to train the system model (12).

Abstract translation: 提供了一种神经网络系统，其在系统模型（12）中对系统进行建模，其输出提供预测输出。 该预测输出由输出控制（14）修改或控制。 在数据预处理步骤（10）中处理输入数据，以便调整用于输入到系统模型（12）的数据。 另外，由和解产生的误差被输入到不确定性模型中，以预测预测输出的不确定性。 这被输入到用于控制输出控制（14）的决策处理器（20）。 控制输出控制器（14），以便在不确定性模型（18）的输出超过由判定阈值块（22）输入的预定判定阈值时改变预测输出或禁止预测输出。 此外，还提供了有效性模型（16），其表示在系统模型（12）的训练期间作为给定数据区域中的数据点的数量的函数的输出的可靠性或有效性。 这预测了也输入到决策处理器（20）的预测输出的置信度。 因此，决策处理器（20）将其决定基于预测的置信度和预测的不确定性。 此外，可以利用数据预处理块（10）输出的不确定性来训练系统模型（12）。

公开(公告)号：US20040122784A1

公开(公告)日：2004-06-24

申请号：US10689888

申请日：2003-10-21

Inventor： David D. Lewis ,  Amitabh Kumar Singhal ,  Daniel L. Stern

IPC: G06N003/08 ,  G06G007/00 ,  G06E003/00 ,  G06E001/00 ,  G06F015/18

CPC classification number: G06N99/005

Abstract: A method and apparatus for communicating accumulated state information between internal and external tasks in a supervised learning system. A supervised learning system encodes state information for a hypothetical learning task on initialization. This hypothetical learning task state information indicates that no training instances have been received. During the supervised learning, training instances are presented to the supervised learner. The training instances are encoded with feature vector and target value information. For each task name paired with a non-default target value, the learner initializes a new learning task by copying the hypothetical learning task state representation for use as the state representation for the new learning task. Predictors are then produced for all learning tasks, except the hypothetical learning task. The new training instance is used to update all learning tasks as specified in the target vector. The new training instance is then used to update the hypothetical learning task state representation as a negative example. Further training instances are handled similarly, new learning tasks are started based on the examination of the sparse target vector for task name, target value pairs which match received training instance target values and for which tasks have not yet been started. The hypothetical state representation information is copied to create the initial state for the new task thereby encapsulating the previous training instances in the new learning tasks state representation.

Abstract translation: 一种用于在监督学习系统中在内部和外部任务之间传送累积状态信息的方法和装置。 监督学习系统在初始化时编码假设学习任务的状态信息。 这种假设的学习任务状态信息表示没有接收到训练实例。 在受监督的学习过程中，培训实例被提供给受监督的学习者。 训练实例使用特征向量和目标值信息进行编码。 对于与非默认目标值配对的每个任务名称，学习者通过复制假设的学习任务状态表达来初始化新的学习任务，以用作新学习任务的状态表示。 然后为所有学习任务生成预测因子，除了假设的学习任务。 新的训练实例用于更新目标向量中指定的所有学习任务。 然后使用新的训练实例来将假设的学习任务状态表示更新为一个负面例子。 进一步训练实例的处理方式类似，基于检查任务名称的稀疏目标向量，匹配接收到的训练实例目标值的目标值对以及哪些任务尚未开始，开始新的学习任务。 复制假设状态表示信息以创建新任务的初始状态，从而将新的训练实例封装在新的学习任务状态表示中。