A VECTOR MATRIX REAL TIME RECURSIVE BACKPROPAGATION ALGORITHM FOR RECURRENT NEURAL NETWORKS THAT APPROXIMATE MULTI-VALUED PERIODIC FUNCTIONS

PETER STUBBERUD

首页> 外文期刊>International Journal of Computational Intelligence and Applications >A VECTOR MATRIX REAL TIME RECURSIVE BACKPROPAGATION ALGORITHM FOR RECURRENT NEURAL NETWORKS THAT APPROXIMATE MULTI-VALUED PERIODIC FUNCTIONS

【24h】

A VECTOR MATRIX REAL TIME RECURSIVE BACKPROPAGATION ALGORITHM FOR RECURRENT NEURAL NETWORKS THAT APPROXIMATE MULTI-VALUED PERIODIC FUNCTIONS

机译：用于近似多值周期函数的递归神经网络的矢量矩阵实时递归反向传播算法

获取原文

获取原文并翻译 | 示例

掌桥外文数据库（机构版） >>

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

Unlike feedforward neural networks (FFNN) which can act as universal function approximators, recursive, or recurrent, neural networks can act as universal approximators for multi-valued functions. In this paper, a real time recursive back-propagation (RTRBP) algorithm in a vector matrix form is developed for a two-layer globally recursive neural network that has multiple delays in its feedback path. This algorithm has been evaluated on two GRNNs that approximate both an analytic and nonanalytic periodic multi-valued function that a feed-forward neural network is not capable of approximating.

机译：与可以用作通用函数逼近器，递归或递归的前馈神经网络（FFNN）不同，神经网络可以用作多值函数的通用逼近器。本文针对两层全局递归神经网络，在反馈路径中存在多个延迟，开发了一种矢量矩阵形式的实时递归反向传播（RTRBP）算法。该算法已在两个GRNN上进行了评估，这两个GRNN都近似前馈神经网络无法近似的解析和非解析周期多值函数。

著录项

来源
《International Journal of Computational Intelligence and Applications》 |2009年第4期|共17页
作者
PETER STUBBERUD;
展开▼
作者单位

展开▼
收录信息
原文格式 PDF
正文语种 eng
中图分类人工智能理论;
关键词
Recurrent neural network (RNN); Real time recursive back-propagation (RTRBP); Globally recurrent neural network (GRNN); System approximation; Hysteresis; Multi-valued periodic functions;

机译：递归神经网络（RNN）;实时递归反向传播（RTRBP）;全局递归神经网络（GRNN）;系统逼近;磁滞;多值周期函数;

相似文献

外文文献
中文文献
专利

1. A VECTOR MATRIX REAL TIME RECURSIVE BACKPROPAGATION ALGORITHM FOR RECURRENT NEURAL NETWORKS THAT APPROXIMATE MULTI-VALUED PERIODIC FUNCTIONS [J] . PETER STUBBERUD International Journal of Computational Intelligence and Applications . 2009,第4期

机译：用于近似多值周期函数的递归神经网络的矢量矩阵实时递归反向传播算法
2. Recurrent Neural Networks Trained With Backpropagation Through Time Algorithm to Estimate Nonlinear Load Harmonic Currents [J] . Mazumdar J., Harley R.G. IEEE Transactions on Industrial Electronics . 2008,第9期

机译：经过时间反向传播训练的递归神经网络，用于估计非线性负载谐波电流
3. Multilayer Feedforward Neural Network Based on Multi-valued Neurons (MLMVN) and a Backpropagation Learning Algorithm [J] . Igor Aizenberg, Claudio Moraga Soft Computing . 2007,第2期

机译：基于多值神经元（MLMVN）和反向传播学习算法的多层前馈神经网络
4. RECURRENT NEURAL NETWORK WITH BACKPROPAGATION THROUGH TIME ALGORITHM FOR ARABIC RECOGNITION [C] . Saliza Ismail, Abdul Manan bin Ahmad European Simulation Multiconference(ESM 2004); 20040613-16; Magdeburg(DE) . 2004

机译：基于时间算法的反向传播递归神经网络
5. A Study of Learning Algorithms for Continuous-Time Recurrent Neural Networks利用統計を見る [D] . Doya Kenji 1991

机译：连续时间递归神经网络的学习算法研究视图使用统计
6. On-Chip Training Spiking Neural Networks Using Approximated Backpropagation With Analog Synaptic Devices [O] . Dongseok Kwon, Suhwan Lim, Jong-Ho Bae, 2020

机译：用模拟突触装置使用近似反向衰减的片上训练尖刺神经网络
7. A vector matrix real time backpropagation algorithm for recurrent neural networks that approximate multi-valued periodic functions [O] . Stubberud Peter 2009

机译：一种近似多值周期函数的递归神经网络向量矩阵实时反向传播算法

A VECTOR MATRIX REAL TIME RECURSIVE BACKPROPAGATION ALGORITHM FOR RECURRENT NEURAL NETWORKS THAT APPROXIMATE MULTI-VALUED PERIODIC FUNCTIONS

摘要

著录项

相似文献

相关主题

期刊订阅