✦ LIBER ✦

Using the EM Algorithm to Train Neural Networks: Misconceptions and a New Algorithm for Multiclass Classification

✍ Scribed by Ng, S.-K.; McLachlan, G.J.

Book ID: 127265854
Publisher: IEEE
Year: 2004
Tongue: English
Weight: 336 KB
Volume: 15
Category: Article
ISSN: 1045-9227
DOI: 10.1109/tnn.2004.826217

No coin nor oath required. For personal study only.

📜 SIMILAR VOLUMES

A novel classification model for cotton

A novel classification model for cotton yarn quality based on trained neural network using genetic algorithm

✍ A.E. Amin 📂 Article 📅 2013 🏛 Elsevier Science 🌐 English ⚖ 458 KB

The Upstart Algorithm: A Method for Cons

The Upstart Algorithm: A Method for Constructing and Training Feedforward Neural Networks

✍ Frean, Marcus 📂 Article 📅 1990 🏛 MIT Press 🌐 English ⚖ 552 KB

A new synthesis approach for feedback ne

A new synthesis approach for feedback neural networks based on the perceptron training algorithm

✍ Liu, D.; Lu, Z. 📂 Article 📅 1997 🏛 IEEE 🌐 English ⚖ 576 KB

Improved results for color error reducti

Improved results for color error reductions using neural networks and a fast training algorithm

✍ Crilly, P.B.; Shaofan Xu 📂 Article 📅 1993 🏛 IEEE 🌐 English ⚖ 360 KB

A comparison study of selected training

A comparison study of selected training algorithms for neural networks with regard to classification of remotely sensed multispectral images

✍ S Murnion; S Kubo 📂 Article 📅 1998 🏛 Elsevier Science 🌐 English ⚖ 577 KB

A simple and efficient approach to train

A simple and efficient approach to train artificial neural networks using a genetic algorithm to calculate the resonant frequency of an RMA on thick substrate

✍ Bonomali Khuntia; Shyam S. Pattnaik; Dhruba C. Panda; Dipak K. Neog; S. Devi; Ma 📂 Article 📅 2004 🏛 John Wiley and Sons 🌐 English ⚖ 249 KB 👁 1 views

## Abstract Both genetic algorithms (GAs) and artificial neural networks (ANNs) have been used in the field of computational electromagnetics as the most powerful optimizing tools. In this paper, a simple and efficient method is presented to handle the problem of competing convention while training