[comp.ai.neural-nets] Favorite Benchmarks for Neural Nets, Anyone?

loren@tristan.llnl.gov (Loren Petrich) (04/03/91)

	This question has occasionally appeared in the NN literature,
and I raise it here.

	What are the most suitable benchmarks for evaluating NN's?

	How might this be a function of the intended application(s)?

	What might be good criteria for selecting benchmarks?

	I have seen:

		The XOR problem
		The parity problem
		The encoder problem

	Any others?


$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$$
Loren Petrich, the Master Blaster: loren@sunlight.llnl.gov

Since this nodename is not widely known, you may have to try:

loren%sunlight.llnl.gov@star.stanford.edu

ylu1@ub.d.umn.edu (Yanzhang Lu) (04/07/91)

The Traveling Salesman Problem.