✦ LIBER ✦

MADALINE Rule II: A training algorithm for neural networks

✍ Scribed by Rodney Winter; Bernard Widrow

Publisher: Elsevier Science
Year: 1988
Tongue: English
Weight: 76 KB
Volume: 1
Category: Article
ISSN: 0893-6080
DOI: 10.1016/0893-6080(88)90187-6

No coin nor oath required. For personal study only.

📜 SIMILAR VOLUMES

Rule extraction from trained neural netw

Rule extraction from trained neural networks using genetic algorithms

✍ A. Duygu Arbatli; H. Levent Akin 📂 Article 📅 1997 🏛 Elsevier Science 🌐 English ⚖ 526 KB

New algorithms for training feedforward

New algorithms for training feedforward neural networks

✍ Subhash Kak 📂 Article 📅 1994 🏛 Elsevier Science 🌐 English ⚖ 270 KB

A parallel algorithm for gradient traini

A parallel algorithm for gradient training of feedforward neural networks

✍ Zdeněk Hanzálek 📂 Article 📅 1998 🏛 Elsevier Science 🌐 English ⚖ 742 KB

This paper presents a message-passing architecture simulating multilayer neural networks, adjusting its weights for each pair, consisting of an input vector and a desired output vector. First, the multilayer neural network is defined, and the difficulties arising from parallel implementation are cla

Improvement of the backpropagation algor

Improvement of the backpropagation algorithm for training neural networks

✍ J. Leonard; M.A. Kramer 📂 Article 📅 1990 🏛 Elsevier Science 🌐 English ⚖ 444 KB

Efficient genetic algorithms for trainin

Efficient genetic algorithms for training layered feedforward neural networks

✍ Byungjoo Yoon; Dawn J. Holmes; Gideon Langholz; Abraham Kandel 📂 Article 📅 1994 🏛 Elsevier Science 🌐 English ⚖ 952 KB

Adaptive stepsize algorithms for on-line

Adaptive stepsize algorithms for on-line training of neural networks

✍ G.D. Magoulas; V.P. Plagianakos; M.N. Vrahatis 📂 Article 📅 2001 🏛 Elsevier Science 🌐 English ⚖ 312 KB

In this paper a method for adapting the stepsize in on-line network training is presented. The proposed technique derives from the stochastic gradient descent proposed by Almeida et al. [On-line Learning in Neural Networks, 111-134, Cambridge University Press, 1998]. The new aspect of our approach c