Online stabilization of block-diagonal recurrent neural networks

Sivakumar S.C.; Robertson W.

首页> 外文期刊>IEEE Transactions on Neural Networks >Online stabilization of block-diagonal recurrent neural networks

【24h】

Online stabilization of block-diagonal recurrent neural networks

机译：块对角递归神经网络的在线稳定

获取原文

获取原文并翻译 | 示例

获取外文期刊封面封底 >>

开具论文收录证明 >>

文献代查 >>

页面导航

摘要
著录项
相似文献
相关主题

摘要

Deals with a discrete-time recurrent neural network (DTRNN) with a block-diagonal feedback weight matrix, called the block-diagonal recurrent neural network (BDRNN), that allows a simplified approach to online training and to address network and training stability issues. The structure of the BDRNN is exploited to modify the conventional backpropagation through time (BPTT) algorithm. To reduce its storage requirement by a numerically stable method of recomputing the network state variables. The network and training stability is addressed by exploiting the BDRNN structure to directly monitor and maintain stability during weight updates by developing a functional measure of system stability that augments the cost function being minimized. Simulation results are presented to demonstrate the performance of the BDRNN architecture, its training algorithm, and the stabilization method.

机译：处理带有块对角反馈权重矩阵的离散时间递归神经网络（DTRNN），称为块对角递归神经网络（BDRNN），该方法可以简化在线培训以及解决网络和培训稳定性问题的方法。利用BDRNN的结构来修改传统的时间反向传播（BPTT）算法。通过重新计算网络状态变量的数值稳定方法来减少其存储需求。网络和训练的稳定性通过开发BDRNN结构来直接监视和维护体重更新过程中的稳定性，方法是开发一种系统稳定性的功能度量，以增强最小化的成本函数。仿真结果表明了BDRNN体系结构的性能，其训练算法和稳定方法。

著录项

来源
《IEEE Transactions on Neural Networks》 |1999年第1期|P.167-175|共9页
作者
Sivakumar S.C.; Robertson W.;
展开▼
作者单位

展开▼
收录信息
原文格式 PDF
正文语种 eng
中图分类自动化技术、计算机技术;
关键词

相似文献

外文文献
中文文献
专利

1. A stable learning algorithm for block-diagonal recurrent neural networks: application to the analysis of lung sounds [J] . Mastorocostas P.A., Theocharis J.B. IEEE transactions on systems, man, and cybernetics. Part B, Cybernetics . 2006,第2期

机译：块对角递归神经网络的稳定学习算法：在肺音分析中的应用
2. Telecommunications call volume forecasting with a block-diagonal recurrent fuzzy neural network [J] . Mastorocostas Paris A., Hilas Constantinos S., Varsamis Dimitris N., Telecommunication systems: Modeling, Analysis, Design and Management . 2016,第1期

机译：块对角递归模糊神经网络的电信呼叫量预测
3. A block-diagonal recurrent fuzzy neural network for system identification [J] . Paris A. Mastorocostas, Constantinos S. Hilas Neural computing & applications . 2009,第7期

机译：块对角递归模糊神经网络的系统辨识
4. A SIMULATED ANNEALING-BASED LEARNING ALGORITHM FOR BLOCK-DIAGONAL RECURRENT NEURAL NETWORKS [C] . Paris A. Mastorocostas, Dimitris N. Varsamis, Constantinos A. Mastorocostas IASTED International Conference on Artificial Intelligence and Applications . 2006

机译：基于模拟退火的块对角线复发性神经网络学习算法
5. Particle Learning and Gated Recurrent Neural Network for Online Tool Wear Diagnosis and Prognosis [D] . Zhang, JianLei. 2017

机译：粒子学习和门控递归神经网络用于在线工具磨损诊断和预后
6. Online Prediction of Ship Behavior with Automatic Identification System Sensor Data Using Bidirectional Long Short-Term Memory Recurrent Neural Network [O] . Miao Gao, Guoyou Shi, Shuang Li 2018

机译：双向长短期记忆递归神经网络通过自动识别系统传感器数据对船舶行为进行在线预测
7. Applying Levenberg-Marquardt algorithm with block-diagonal Hessian approximation to recurrent neural network training. [O] . 1999

机译：applying Levenberg-marquardt algorithm with block-diagonal Hessian approximation to recurrent neural network training.

Online stabilization of block-diagonal recurrent neural networks

摘要

著录项

相似文献

相关主题

期刊订阅