Pattern Recognition System using Evolvable Hardware
We have developed a high-speed pattern recognition system using
evolvable hardware (EHW) in 1996. The purpose of the system is to
show that recognition devices based on EHW are possible and that they
have the same robustness against noise as devices based on an
artificial neural network (ANN). The advantage of EHW compared with
ANN is the high processing speed and the readability of the learned
result. We confirmed the advantage with an experiment on recognizing
the binary patterns of 8 x 8 pixels. We also compared the processing
speed of the pattern recognition system with two types of fastest
class ANN dedicated hardware. The recognition speed of the EHW was
the fastest; 1.7 times as fast as that of CNAPS, and 9.2 times as
fast as that of MY-NEUPOWER.
Fig. 1 The pattern recognition system using EHW.

Fig. 2 Block diagram of pattern recognition system.
Fig. 3 The EHW board.
Related papers in our publication list:
English: No.
011,
007,
010,
018,
Japanese: No.
004
If you have any questions or comments in this page, send email to
M. Iwata.