๐”– Bobbio Scriptorium
โœฆ   LIBER   โœฆ

Reducing the Dimensionality of Data with Neural Networks

โœ Scribed by Hinton, G. E.

Book ID
118049203
Publisher
American Association for the Advancement of Science
Year
2006
Tongue
English
Weight
361 KB
Volume
313
Category
Article
ISSN
0036-8075

No coin nor oath required. For personal study only.

๐Ÿ“œ SIMILAR VOLUMES

Reducing data dimensionality through opt
Reducing data dimensionality through optimizing neural network inputs
โœ Shufeng Tan; Michael L. Mayrovouniotis ๐Ÿ“‚ Article ๐Ÿ“… 1995 ๐Ÿ› American Institute of Chemical Engineers ๐ŸŒ English โš– 916 KB

A neural network method for reducing data dimensionality based on the concept of input training, in which each input pattern is not fKed but adjusted along with internal network parameters to reproduce its corresponding output pattern, is presented. With input adjustment, a properly configured netwo

Training neural networks with heterogene
Training neural networks with heterogeneous data
โœ John A. Drakopoulos; Ahmad Abdulkader ๐Ÿ“‚ Article ๐Ÿ“… 2005 ๐Ÿ› Elsevier Science ๐ŸŒ English โš– 140 KB

Data pruning and ordered training are two methods and the results of a small theory that attempts to formalize neural network training with heterogeneous data. Data pruning is a simple process that attempts to remove noisy data. Ordered training is a more complex method that partitions the data into

Dynamic neural networks with data assimi
Dynamic neural networks with data assimilation
โœ Henk van den Boogaard; Arthur Mynett ๐Ÿ“‚ Article ๐Ÿ“… 2004 ๐Ÿ› John Wiley and Sons ๐ŸŒ English โš– 142 KB

Neural networks (NNs) are often used as black-box techniques for the modelling of system relations. Standard NNs are static models, whereas in practice one often has to deal with dynamic systems or processes. In such cases, dynamic neural networks (DNNs) may be better suited. We will argue that the