"

欢迎来到亚博yabo24_官网首页(yabovip6666.cn)全新升级娱乐网站。亚博yabo24_官网首页综合各种在线游戏于一站式的大型游戏平台,经营多年一直为大家提供安全稳定的游戏环境,亚博yabo24_官网首页致力于提供全球客户有价值的游戏,为用户提供优质服务。

    <sub id="rfprx"></sub>

    <thead id="rfprx"><var id="rfprx"><output id="rfprx"></output></var></thead>

    <form id="rfprx"></form>
    <address id="rfprx"><dfn id="rfprx"></dfn></address><sub id="rfprx"></sub>

    <sub id="rfprx"><var id="rfprx"></var></sub>

      <sub id="rfprx"><dfn id="rfprx"></dfn></sub><form id="rfprx"><dfn id="rfprx"></dfn></form>
      <sub id="rfprx"><dfn id="rfprx"><ins id="rfprx"></ins></dfn></sub>

      <sub id="rfprx"><dfn id="rfprx"><ins id="rfprx"></ins></dfn></sub>

      <sub id="rfprx"><dfn id="rfprx"><ins id="rfprx"></ins></dfn></sub>

      <address id="rfprx"><listing id="rfprx"><ins id="rfprx"></ins></listing></address>

      <sub id="rfprx"></sub>

      <address id="rfprx"><dfn id="rfprx"><output id="rfprx"></output></dfn></address>

      <address id="rfprx"><var id="rfprx"></var></address>
      <address id="rfprx"><dfn id="rfprx"></dfn></address>
      <sub id="rfprx"></sub>

      <sub id="rfprx"><dfn id="rfprx"><output id="rfprx"></output></dfn></sub><form id="rfprx"><dfn id="rfprx"></dfn></form>

      <thead id="rfprx"><var id="rfprx"><output id="rfprx"></output></var></thead>
          <thead id="rfprx"><var id="rfprx"><output id="rfprx"></output></var></thead>
          <sub id="rfprx"><dfn id="rfprx"><output id="rfprx"></output></dfn></sub>
          <sub id="rfprx"><dfn id="rfprx"></dfn></sub>

            <sub id="rfprx"><var id="rfprx"></var></sub>
            "
            将本页翻译成中文
            您现在的位置:首页> 外文学位 >文献详情

            【6h】 Architecture optimization, training convergence and network estimation robustness of a fully connected recurrent neural network.

            【摘要】Recurrent neural networks (RNN) have been rapidly developed in recent years. Applications of RNN can be found in system identification, optimization, image processing, pattern reorganization, classification, clustering, memory association, etc.;In this study, an optimized RNN is proposed to model nonlinear dynamical systems. A fully connected RNN is developed first which is modified from a fully forward connected neural network (FFCNN) by accommodating recurrent connections among its hidden neurons. In addition, a destructive structure optimization algorithm is applied and the extended Kalman filter (EKF) is adopted as a network's training algorithm. These two algorithms can seamlessly work together to generate the optimized RNN. The enhancement of the modeling performance of the optimized network comes from three parts: (1) its prototype - the FFCNN has advantages over multilayer perceptron network (MLP), the most widely used network, in terms of modeling accuracy and generalization ability; (2) the recurrency in RNN network make it more capable of modeling non-linear dynamical systems; and (3) the structure optimization algorithm further improves RNN's modeling performance in generalization ability and robustness.;Performance studies of the proposed network are highlighted in training convergence and robustness. For the training convergence study, the Lyapunov method is used to adapt some training parameters to guarantee the training convergence, while the maximum likelihood method is used to estimate some other parameters to accelerate the training process. In addition, robustness analysis is conducted to develop a robustness measure considering uncertainties propagation through RNN via unscented transform.;Two case studies, the modeling of a benchmark non-linear dynamical system and a tool wear progression in hard turning, are carried out to testify the development in this dissertation.;The work detailed in this dissertation focuses on the creation of: (1) a new method to prove/guarantee the training convergence of RNN, and (2) a new method to quantify the robustness of RNN using uncertainty propagation analysis. With the proposed study, RNN and related algorithms are developed to model nonlinear dynamical system which can benefit modeling applications such as the condition monitoring studies in terms of robustness and accuracy in the future.

            【原文格式】PDF

            联系方式:18141920177 (微信同号)

            客服邮箱:kefu@zhangqiaokeyan.com

            京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-1 六维联合信息科技 (北京) 有限公司?版权所有
            • 客服微信

            • 服务号

            亚博yabo24_官网首页

              <sub id="rfprx"></sub>

              <thead id="rfprx"><var id="rfprx"><output id="rfprx"></output></var></thead>

              <form id="rfprx"></form>
              <address id="rfprx"><dfn id="rfprx"></dfn></address><sub id="rfprx"></sub>

              <sub id="rfprx"><var id="rfprx"></var></sub>

                <sub id="rfprx"><dfn id="rfprx"></dfn></sub><form id="rfprx"><dfn id="rfprx"></dfn></form>
                <sub id="rfprx"><dfn id="rfprx"><ins id="rfprx"></ins></dfn></sub>

                <sub id="rfprx"><dfn id="rfprx"><ins id="rfprx"></ins></dfn></sub>

                <sub id="rfprx"><dfn id="rfprx"><ins id="rfprx"></ins></dfn></sub>

                <address id="rfprx"><listing id="rfprx"><ins id="rfprx"></ins></listing></address>

                <sub id="rfprx"></sub>

                <address id="rfprx"><dfn id="rfprx"><output id="rfprx"></output></dfn></address>

                <address id="rfprx"><var id="rfprx"></var></address>
                <address id="rfprx"><dfn id="rfprx"></dfn></address>
                <sub id="rfprx"></sub>

                <sub id="rfprx"><dfn id="rfprx"><output id="rfprx"></output></dfn></sub><form id="rfprx"><dfn id="rfprx"></dfn></form>

                <thead id="rfprx"><var id="rfprx"><output id="rfprx"></output></var></thead>
                    <thead id="rfprx"><var id="rfprx"><output id="rfprx"></output></var></thead>
                    <sub id="rfprx"><dfn id="rfprx"><output id="rfprx"></output></dfn></sub>
                    <sub id="rfprx"><dfn id="rfprx"></dfn></sub>

                      <sub id="rfprx"><var id="rfprx"></var></sub>