𝔖 Bobbio Scriptorium
✦   LIBER   ✦

Efficient Partition of Learning Data Sets for Neural Network Training

✍ Scribed by Igor V. Tetko; Alessandro E.P. Villa

Publisher
Elsevier Science
Year
1997
Tongue
English
Weight
641 KB
Volume
10
Category
Article
ISSN
0893-6080

No coin nor oath required. For personal study only.

✦ Synopsis

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 domains of the data set and accelerate the learning phase. The proposed algorithm provides a good prediction accuracy using fewer cases from non-informative domains according to a correlative measure of dependency between cases of the training set. This measure takes into account internal relationships amid analyzed data and can be used to cluster neighbor cases in a multidimensional space and to filter out the outliers. The possible relation of the proposed algorithm to brain processing occurring in the thalamocortical pathway is discussed. α­§ 1997 Elsevier Science Ltd.

πŸ“œ SIMILAR VOLUMES

Hybrid learning schemes for fast trainin
Hybrid learning schemes for fast training of feed-forward neural networks
✍ Nicolaos B. Karayiannis πŸ“‚ Article πŸ“… 1996 πŸ› Elsevier Science 🌐 English βš– 905 KB

Fast training of feed-forward neural networks became increasingly important as the neural network field moves toward maturity. This paper begins with a review of various criteria proposed for training feed-forward neural networks, which include the frequently used quadratic error criterion, the rela

On a class of efficient learning algorit
On a class of efficient learning algorithms for neural networks
✍ Frank BΓ€rmann; Friedrich Biegler-KΓΆnig πŸ“‚ Article πŸ“… 1992 πŸ› Elsevier Science 🌐 English βš– 457 KB

The ability of a neural network with one hidden layer to accurately learn a specified learning set increases with the number of nodes in the hidden layer; if a network has exactly the same number of internal nodes as the number of examples to be learnt, it is theoretically able to learn these exampl