next up previous
Next: The line search Up: Practical Implementation Issues Previous: Dynamic Learning Parameters

Conjugate Gradient Learning

Several things must be kept in mind when using the CG option in JETNET 3.0 since it is a batch-type learning algorithm that depends strongly on the uniqueness of the error function. Most importantly, an identical set of training patterns must be used for each evaluation of the error, otherwise the line search gets confused.

System PRIVILEGED Account
Fri Feb 24 11:28:59 MET 1995