next up previous contents index
Next: Architecture-coupled methods Up: Learning algorithms for DTRNN Previous: Other derivative-based methods   Contents   Index


Non-gradient methods

Gradient-based algorithms are the most used of all learning algorithms for DTRNN. But there are also some interesting non-gradient-based algorithms, most of which rely on weight perturbation schemes. Of those, two batch learning algorithms are worth mentioning:


next up previous contents index
Next: Architecture-coupled methods Up: Learning algorithms for DTRNN Previous: Other derivative-based methods   Contents   Index
Debian User 2002-01-21