Trans-Dimensional Learning:

This is a Windows 3.1 artificial neural netwrk and GA program (shareware). TDL allows users to perform pattern recognition by utilizing software that allows for fast, automatic construction of Neural Networks, mostly alleviating the need for parameter tuning. Evolutionary processes combined with semi-weighted networks (hybrid cross between standard weighted neurons and weightless n-level threshold units) generally yield very compact networks (i.e., reduced connections and hidden units). By supporting multi-shot learning over standard one-shot learning, multiple data sets (characterized by varying input and output dimensions) can be learned incrementally, resulting in a single coherent network. This can also lead to significant improvements in predictive accuracy (Trans-dimensional generalization). Graphical support and several data files are also provided.

Available on the WWW from: http://pages.prodigy.com/upso

For further details contact: <upso@prodigy.com>


[Free Software List] [Commercial Software List] [Research Projects] [HHGTEC main contents page]

Mistakes in this page?
Hitch Hiker's Guide to Evolutionary Computation, Issue 6.4, released 21 December 1998
Copyright © 1993-1998 by J. Heitkötter and D. Beasley, all rights reserved.