Zusammenfassung
An evolutionary algorithm implemented in hardware is
expected to operate much faster than the equivalent
software implementation. However, this may not be true
for slow fitness evaluation applications. This paper
introduces a fast evolutionary algorithm (FEA) that
does not evaluate all new individuals, thus operating
faster for slow fitness evaluation applications.
Results of a hardware implementation of this algorithm
are presented that show the real time advantages of
such systems for slow fitness evaluation applications.
Results are presented for six optimisation functions
and for image compression hardware.
Nutzer