Technical Reports

1991

@techreport{HoF1991,
	vgclass =	{report},
	vgproject =	{nn},
	author =	{Markus Hoefeld and Scott E. Fahlman},
	title =	{Learning with Limited Numerical Precision Using the
	{C}ascade-{C}orrelation Algorithm},
	number =	{CMU-CS-91-130},
	institution =	{School of Computer Science, Carnegie Mellon University},
	address =	{Pittsburgh, PA 15213},
	month =	{May},
	year =	{1991},
	abstract =	{A key question in the design of specialized hardware for
	simulation of neural networks is whether fixed point arithmetic of
	limited numerical precision can be used with existing learning
	algorithms. We present an empirical study of the effects of limited
	precision in Cascade-Correlation networks on three different learning
	problems. We show that learning can fail abruptly as the precision of
	network weights or weight-update calculations is reduced below 12 bits.
	We introduce techniques for dynamic rescaling and probabilistic
	rounding that allow reliable convergence down to 6 bits of precision,
	with only a gradual reduction in the quality of the solutions.},
}