|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|
Many people view neural networks as magic and capable of doing absolutely anything. Here are some articles that provide an anti-dote to that mania. An article by Andy Clark and Chris Thornton that references an article by Jeff Elman An article by Kevin Swingler discusses the pitfalls of using backprop on financial time series data.