Copyright 1996-2001 by Donald R. Tveter, commercial use is prohibited. Short quotations are permitted if proper attribution is given. This material CAN be posted elsewhere on the net if the posted files are not altered in any way but please let me know where it is posted. The main location is: http://dontveter.com/bpr/bpr.html |
An online html version of a paper by Charles Lam and others concerns predicting stock market performance. You can also follow the above link to his online thesis, which unfortunately is in Microsoft Word format rather than postscript.
There is an online article by McCann and Kalman on trying to predict the tops and bottoms of the gold market.
There is an online article by Kevin Swingler that deals with the pitfalls of economic forecasting.
There is an online article by Utans and Moody that deals with predicting the ratings of corporate bonds and another offline article on bond rating.
There is an online article by Giles, Lawrence and Tsoi on using recurrent networks to predict currency fluctuations.
There is an online article by Neal, Goodacre and Kell that deals with the analysis of pyrolysis mass spectra.
There is a rather long and detailed but highly readable offline article on the system ALVINN from Carnegie-Mellon that using backprop learned to drive on all sorts of roads. There is also some online material on this system from Carnegie-Mellon.
There is an online and offline article on using backprop for predicting the results of greyhound racing.
I put together a short tutorial on coding data for character recognition.