✦ LIBER ✦

Linearization learning method of BP neural networks

✍ Scribed by Zhou Shaoqian; Ding Lixin; Zhang Jian; Tang Xinhua

Publisher: Wuhan University
Year: 1997
Tongue: English
Weight: 297 KB
Volume: 2
Category: Article
ISSN: 1007-1202
DOI: 10.1007/bf02834910

No coin nor oath required. For personal study only.

📜 SIMILAR VOLUMES

Convergence analysis of online gradient

Convergence analysis of online gradient method for BP neural networks

✍ Wei Wu; Jian Wang; Mingsong Cheng; Zhengxue Li 📂 Article 📅 2011 🏛 Elsevier Science 🌐 English ⚖ 297 KB

This paper considers a class of online gradient learning methods for backpropagation (BP) neural networks with a single hidden layer. We assume that in each training cycle, each sample in the training set is supplied in a stochastic order to the network exactly once. It is interesting that these sto

A Method of Accelerating Neural Network

A Method of Accelerating Neural Network Learning

✍ Sotir Sotirov 📂 Article 📅 2005 🏛 Springer US 🌐 English ⚖ 134 KB

A learning method of immune multi-agent

A learning method of immune multi-agent neural networks

✍ Takumi Ichimura; Shinichi Oeda; Machi Suka; Katsumi Yoshida 📂 Article 📅 2004 🏛 Springer-Verlag 🌐 English ⚖ 953 KB

Anti-Hebbian learning in a non-linear ne

Anti-Hebbian learning in a non-linear neural network

✍ A. Carlson 📂 Article 📅 1990 🏛 Springer-Verlag 🌐 English ⚖ 604 KB

A new learning method using prior inform

A new learning method using prior information of neural networks

✍ Baiquan Lu; Kotaro Hirasawa; Junichi Murata 📂 Article 📅 2000 🏛 Springer Japan 🌐 English ⚖ 439 KB

A method of BP network learning by expan

A method of BP network learning by expanding the distribution of category

✍ Naoki Tanaka; Toshiaki Koreyeda; Takeshi Inoue; Koji Kajitani 📂 Article 📅 1999 🏛 John Wiley and Sons 🌐 English ⚖ 300 KB

In backpropagation networks, unlearned regions are left between categories if the learning samples are comparatively small. Such unlearned regions are one of the reasons for the degradation of network generalization ability. To improve the generalization ability, it is preferable that the boundaries