✦ LIBER ✦

Learning criteria for training neural network classifiers

✍ Scribed by P. Zhou; J. Austin

Publisher: Springer-Verlag
Year: 1998
Tongue: English
Weight: 785 KB
Volume: 7
Category: Article
ISSN: 0941-0643
DOI: 10.1007/bf01428124

No coin nor oath required. For personal study only.

📜 SIMILAR VOLUMES

Simultaneous design and training of onto

Simultaneous design and training of ontogenic neural network classifiers

✍ James P. Ignizio; James R. Soltys 📂 Article 📅 1996 🏛 Elsevier Science 🌐 English ⚖ 707 KB

Revisiting squared-error and cross-entro

Revisiting squared-error and cross-entropy functions for training neural network classifiers

✍ Douglas M. Kline; Victor L. Berardi 📂 Article 📅 2005 🏛 Springer-Verlag 🌐 English ⚖ 571 KB

Efficient Partition of Learning Data Set

Efficient Partition of Learning Data Sets for Neural Network Training

✍ Igor V. Tetko; Alessandro E.P. Villa 📂 Article 📅 1997 🏛 Elsevier Science 🌐 English ⚖ 641 KB

This study investigates the emerging possibilities of combining unsupervised and supervised learning in neural network ensembles. Such strategy is used to get an efficient partition of a noisy input data set in order to focus the training of neural networks on the most complex and informative domain

A scatter-search-based learning algorith

A scatter-search-based learning algorithm for neural network training

✍ James P. Kelly; Balasubramanian Rangaswamy; Jiefeng Xu 📂 Article 📅 1996 🏛 Springer US 🌐 English ⚖ 931 KB

Supervised extended ART: A fast neural n

Supervised extended ART: A fast neural network classifier trained by combining supervised and unsupervised learning

✍ Hahn-Ming Lee; Chia-Shing Lai 📂 Article 📅 1996 🏛 Springer US 🌐 English ⚖ 963 KB

The eigenspace separation transform for

The eigenspace separation transform for neural-network classifiers

✍ Don Torrieri 📂 Article 📅 1999 🏛 Elsevier Science 🌐 English ⚖ 156 KB

This paper presents a linear transform that compresses data in a manner designed to improve the performance of a neural network used as a binary classifier. The classifier is intended to accommodate data distributions that may be non-normal, may have equal class means, may be multimodal, and have un