Forward Propagation Universal Learning Network

Kotaro HIRASAWA; Masanao Ohbayashi; Masaru Koga

首页> 外文期刊>Memoirs of the Faculty of Engineering KYUSHU University >Forward Propagation Universal Learning Network

【24h】

Forward Propagation Universal Learning Network

机译：正向传播通用学习网络

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

In this paper, a computing method of higher order derivatives of Universal Learning Network(U.L.N.) is derived by forward propagation, and U.L.N. is extended so that multiplex branch from node to node may be built in U.L.N.. It is shown by comparing with backward propagation and forward propagation that forward propagation is preferable to backward propagation in computation time when higher order derivatives with respect to time invariant parameters should be calculated. It is also suggested that robust control and chaotic control can be realized if higher order derivatives are available.

机译：本文通过前向传播推导了通用学习网络（U.L.N.）的高阶导数的计算方法。通过扩展，以便可以在ULN中建立从一个节点到另一个节点的多路复用分支，通过与反向传播和正向传播进行比较，可以看出，当应使用相对于时不变参数的高阶导数时，正向传播在计算时间上优于反向传播。计算。还建议如果可以使用高阶导数，则可以实现鲁棒控制和混沌控制。

著录项

来源
《Memoirs of the Faculty of Engineering KYUSHU University》 |1995年第3期|p.225-234|共10页
作者
Kotaro HIRASAWA; Masanao Ohbayashi; Masaru Koga;
展开▼
作者单位

Department of Electrical Engineering;

展开▼
收录信息
原文格式 PDF
正文语种 eng
中图分类一般工业技术;
关键词
universal learning network; higher order derivatives; gradient method; neural network;

机译：通用学习网络;高阶导数;梯度法;神经网络;

相似文献

外文文献
中文文献
专利

1. Propagation and control of stochastic signals through universal learning networks. [J] . Hirasawa K, Mabu S, Hu J Neural Networks: The Official Journal of the International Neural Network Society . 2006,第4期

机译：通过通用学习网络传播和控制随机信号。
2. FEED-FORWARD NEURAL NETWORKS TRAINING: A COMPARISON BETWEEN GENETIC ALGORITHM AND BACK-PROPAGATION LEARNING ALGORITHM [J] . Zhen-Guo Che, Tzu-An Chiang, Zhen-Hua Che International Journal of Innovative Computing Information and Control . 2011,第10期

机译：前馈神经网络训练：遗传算法与反向传播学习算法的比较
3. A Forward-Propagation Learning Rule for Acquiring Inverse Models in Multilayered Neural Networks [J] . Kazuyuki Nagasawa, Naohiro Fukumura, Yoji Uno Electronics and Communications in Japan. Part 2, Electronics . 2005,第2期

机译：多层神经网络中获取逆模型的正向传播学习规则
4. Forward propagation universal learning network [C] . Hirasawa, K., Ohbayashi, . 1996

机译：前向传播通用学习网络
5. An evaluation of feed-forward, back-propagation neural networks for optimal design of structural systems and for modular analysis of electronic packages. [D] . Zhang, Li. 2001

机译：对前馈，后向传播神经网络的评估，用于结构系统的最佳设计和电子封装的模块化分析。
6. Feed-Forward Propagation of Temporal and Rate Information between Cortical Populations during Coherent Activation in Engineered In Vitro Networks [O] . Thomas B. DeMarse, Liangbin Pan, Sankaraleengam Alagapan, 2016

机译：工程体外网络中相干激活过程中皮质种群之间的时间和速率信息的前馈传播
7. A Fast Incremental Learning Algorithm for Feed-forward Neural Networks Using Resilient Propagation [O] . Joseph Annie anak, Ozawa Seiichi 2014

机译：基于弹性传播的前馈神经网络快速增量学习算法

Forward Propagation Universal Learning Network

摘要

著录项

相似文献

相关主题

期刊订阅