公开(公告)号：US08126859B2

公开(公告)日：2012-02-28

申请号：US11388012

申请日：2006-03-23

Applicant: Cale T. Rath ,  Megan Erin Williams

Inventor： Cale T. Rath ,  Megan Erin Williams

IPC: G06F7/00 ,  G06F17/00 ,  G06F15/16

CPC classification number: G06F17/3002 ,  G06F17/30174

Abstract: In an embodiment, a local version of a file is found in response to detecting an access of a remote version of the file. In response to the detecting, a determination is made whether the remote version meets a rule, and if the rule is met, then the local version is updated with the remote version of the file if the remote version is valid. The rule may be customized for the file. In various embodiments, the determination includes determining whether the remote version of the file was created more recently than the local version, whether the remote version has a level that is greater than the level of the local version, or whether the remote version is stored at a source location specified by the rule. In various embodiments, the level may be an audio or video quality of the file or an update identifier of the file. In this way, out-of date local versions of files may be updated with newer or better remote versions of files.

Abstract translation: 在一个实施例中，响应于检测到文件的远程版本的访问，找到文件的本地版本。 响应于检测，确定远程版本是否符合规则，如果符合规则，则如果远程版本有效，则使用文件的远程版本更新本地版本。 可以为文件定制规则。 在各种实施例中，确定包括确定文件的远程版本是否比本地版本更近地被创建，远程版本是否具有大于本地版本的级别的级别，或者远程版本是否存储在 由规则指定的源位置。 在各种实施例中，该级别可以是文件的音频或视频质量或文件的更新标识符。 以这种方式，可能会使用更新或更好的远程版本的文件更新本地版本的文件。

公开(公告)号：USD685470S1

公开(公告)日：2013-07-02

申请号：US29395477

申请日：2012-01-27

Applicant: Dennis Schroeder ,  Eric Schmid ,  Eric Olson ,  Chris Clark ,  Jonathan Abarbanel ,  Bernard Lo ,  Erin Williams ,  Cynthia Kossayan ,  Stuart Karten

Designer： Dennis Schroeder ,  Eric Schmid ,  Eric Olson ,  Chris Clark ,  Jonathan Abarbanel ,  Bernard Lo ,  Erin Williams ,  Cynthia Kossayan ,  Stuart Karten

公开(公告)号：US06622135B1

公开(公告)日：2003-09-16

申请号：US09465088

申请日：1999-12-16

Applicant: Gislain Imbert De Tremiolles ,  Pascal Tannhof ,  Erin Williams

Inventor： Gislain Imbert De Tremiolles ,  Pascal Tannhof ,  Erin Williams

IPC: G06N306

CPC classification number: G06K9/6276 ,  G06T7/0004 ,  G06T2207/30148

Abstract: 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.

Abstract translation: 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。