利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

13 条记录 (耗时 0.037 秒)

    Method for training a neural network
    1.
    发明授权
    Method for training a neural network 有权
    训练神经网络的方法

    公开(公告)号：US06968327B1

    公开(公告)日：2005-11-22

    申请号：US10049650

    申请日：2000-08-24

    申请人： Ronald Kates ,  Nadia Harbeck ,  Manfred Schmitt

    发明人： Ronald Kates ,  Nadia Harbeck ,  Manfred Schmitt

    IPC分类号： A61B5/00 ,  G06F19/00 ,  G06N3/08 ,  G06E1/00 ,  G06E3/00 ,  G06F15/18 ,  G06G7/00

    CPC分类号： G06N3/08 ,  A61B5/00 ,  A61B5/415 ,  A61B5/418 ,  A61B5/7267 ,  G06F19/00

    摘要： A method for training a neural network in order to optimize the structure of the neural network includes identifying and eliminating synapses that have no significant influence on the curve of the risk function. First and second sending neurons are selected that are connected to the same receiving neuron by respective first and second synapses. It is assumed that there is a correlation of response signals from the first and second sending neurons to the same receiving neuron. The first synapse is interrupted and a weight of the second synapse is adapted in its place. The output signals of the changed neural network are compared with the output signals of the unchanged neural network. If the comparison result does not exceed a predetermined level, the first synapse is eliminated, thereby simplifying the structure of the neural network.

    摘要翻译： 用于训练神经网络以优化神经网络的结构的方法包括识别和消除对风险函数的曲线没有显着影响的突触。 选择通过相应的第一和第二突触连接到相同接收神经元的第一和第二发送神经元。 假设存在来自第一和第二发送神经元到相同接收神经元的响应信号的相关性。 第一突触中断，第二突触的重量适应其位置。 将改变的神经网络的输出信号与不变神经网络的输出信号进行比较。 如果比较结果不超过预定水平，则消除第一突触，从而简化了神经网络的结构。

    Methods for selecting treatment regimens and predicting outcomes in cancer patients
    2.
    发明申请
    Methods for selecting treatment regimens and predicting outcomes in cancer patients 审中-公开
    选择治疗方案和预测癌症患者结局的方法

    公开(公告)号：US20060084056A1

    公开(公告)日：2006-04-20

    申请号：US10504287

    申请日：2003-02-13

    申请人： Nadia Harbeck ,  Manfred Schmitt ,  John Foekens ,  Ronald Kates

    发明人： Nadia Harbeck ,  Manfred Schmitt ,  John Foekens ,  Ronald Kates

    IPC分类号： C12Q1/68 ,  C12P19/34

    CPC分类号： C12Q1/6886 ,  C12Q2600/106 ,  C12Q2600/112 ,  C12Q2600/118 ,  C12Q2600/136 ,  G01N33/57415 ,  G01N2800/52 ,  Y02A90/26

    摘要： The present invention relates to methods for determining a treatment regimen beyond surgical removal of tumor tissue for node negative or node positive breast cancer patient. The method comprises measuring the levels of urokinase-type plasminogen activator (uPA) and plasminogen activator inhibitor-1 (PAI-1) in a subject, preferably a tumor; and, based upon the values, predicting the expected benefit including disease-free survival and/or overall survival for the patient without treatment (beyond the surgical removal of tumor tissue) or with a particular treatment and using that information to select a treatment regimen for the subject. High risk subject is identified by high levels of both uPA and PAI-1, high level of uPA and low level of PAI-1 or, low level of uPA and high level of PAI-1. Treatment options for high risk subjects include, but are not limited to, adjuvant CMF chemotherapy, adjuvant non-CMF chemotherapy, adjuvant endocrine therapy, adjuvant anthracyclin-containing chemotherapy, radiation therapy, and gene therapy. Treatment options for low risk subjects include, but are not limited to, no treatment, radiation, and adjuvant endocrine therapy.

    摘要翻译： 本发明涉及用于确定除了手术切除淋巴结阴性或淋巴结阳性乳腺癌患者的肿瘤组织之外的治疗方案的方法。 该方法包括测量受试者，优选肿瘤中尿激酶型纤溶酶原激活物（uPA）和纤溶酶原激活物抑制剂-1（PAI-1）的水平; 并且基于这些值，预测未经治疗的患者（超过手术切除肿瘤组织）或特定治疗的患者的无病生存期和/或总生存期的预期益处，并且使用该信息来选择治疗方案 主题。 uPA和PAI-1水平高，uPA水平高，PAI-1水平低，uPA水平低，PAI-1水平高。 高风险患者的治疗方案包括但不限于辅助性CMF化疗，辅助性非CMF化疗，辅助内分泌治疗，含蒽环类化疗，放射治疗和基因治疗。 低风险患者的治疗方案包括但不限于治疗，放射和辅助内分泌治疗。

    Method for training a learning-capable system
    4.
    发明申请
    Method for training a learning-capable system 有权
    培养学习能力的系统的方法

    公开(公告)号：US20060248031A1

    公开(公告)日：2006-11-02

    申请号：US10520409

    申请日：2003-07-03

    申请人： Ronald Kates ,  Nadia Harbeck

    发明人： Ronald Kates ,  Nadia Harbeck

    IPC分类号： G06F15/18 ,  G06N3/02

    CPC分类号： G16H50/20 ,  G06F19/00

    摘要： The invention is directed to a method for training at least one learning-capable system comprising the steps of providing a predetermined training data set corresponding to a predetermined number of subjects comprising a predetermined input data set and a predetermined outcome data set, augmenting the input data set and/or the outcome data set, and training each learning-capable system using the augmented input data set and/or the augmented outcome data set.

    摘要翻译： 本发明涉及用于训练至少一个学习能力系统的方法，包括以下步骤：提供对应于预定数量的对象的预定训练数据集，所述预定训练数据集包括预定输入数据集和预定结果数据集，增加输入数据 设置和/或结果数据集，并且使用增强输入数据集和/或增强结果数据集来训练每个具有学习能力的系统。