Model Development A Short Primer

The previous section introduced the backpropagation rule for multi-layer percep-trons. This section briefly discusses tfie model development cycle necessary ftu-obtaining a properly functioning net. It also touches upon some of the available heuristics for determining the proper size of hidden layers. 

Fundamentally, all feed-forward backpropagating nets follow the same five basic steps of a model development cycle  

In cannot be stressed strongly enough that the first step, defining the. problem, is far from being a simple task. Great care must be taken to identify precisely what one wishes for the net to learn.  

The obvious lesson to be taken away from this amusing example is that how well a net learns the desired associations depends almost entirely on how well the database of facts is defined. Just as Monte Carlo simulations in statistical mechanics may fall short of intended results if they are forced to rely upon poorly coded random number generators, so do backpropagating nets typically fail to ac hieve expected re.sults if the facts they are trained on are statistically corrupt. 

The task becomes a little bit more tricky when it comes to selecting an appropriate number of (and size for) the hidden layers. 

---