In this paper, we propose evolvable reasoning hardware
and its design methodology. In the proposed design
methodology, case databases of each reasoning task are
transformed into truth tables, which are evolved to
extract rules behind the past cases through a genetic
algorithm. Circuits for the evolvable reasoning
hardware are synthesized from the evolved truth-tables.
Parallelism in each task can be embedded directly in
the circuits through the direct hardware implementation
of the case databases. We developed the evolvable
reasoning hardware prototype using Xilinx Virtex FPGA
chips and applied it to the
English-pronunciation-reasoning (EPR) task. The
evolvable reasoning hardware for the EPR task was
implemented with 270K gates, achieving an extremely
high reasoning speed of less than 300 ns/phoneme. It
also achieved a reasoning accuracy of 82.1% which is
almost the same accuracy as NETTalk in neural networks
and MBRTalk in parallel AI.
%0 Journal Article
%1 yasunaga:2001:GPEM
%A Yasunaga, Moritoshi
%A Kim, Jung Hwan
%A Yoshihara, Ikuo
%D 2001
%J Genetic Programming and Evolvable Machines
%K FPGA, MBRTalk NETTalk, VLSI algorithms, design evolvable genetic hardware, methodology, reasoning,
%N 3
%P 211--230
%R doi:10.1023/A:1011939025340
%T Evolvable Reasoning Hardware: Its Prototyping and
Performance Evaluation
%V 2
%X In this paper, we propose evolvable reasoning hardware
and its design methodology. In the proposed design
methodology, case databases of each reasoning task are
transformed into truth tables, which are evolved to
extract rules behind the past cases through a genetic
algorithm. Circuits for the evolvable reasoning
hardware are synthesized from the evolved truth-tables.
Parallelism in each task can be embedded directly in
the circuits through the direct hardware implementation
of the case databases. We developed the evolvable
reasoning hardware prototype using Xilinx Virtex FPGA
chips and applied it to the
English-pronunciation-reasoning (EPR) task. The
evolvable reasoning hardware for the EPR task was
implemented with 270K gates, achieving an extremely
high reasoning speed of less than 300 ns/phoneme. It
also achieved a reasoning accuracy of 82.1% which is
almost the same accuracy as NETTalk in neural networks
and MBRTalk in parallel AI.
@article{yasunaga:2001:GPEM,
abstract = {In this paper, we propose evolvable reasoning hardware
and its design methodology. In the proposed design
methodology, case databases of each reasoning task are
transformed into truth tables, which are evolved to
extract rules behind the past cases through a genetic
algorithm. Circuits for the evolvable reasoning
hardware are synthesized from the evolved truth-tables.
Parallelism in each task can be embedded directly in
the circuits through the direct hardware implementation
of the case databases. We developed the evolvable
reasoning hardware prototype using Xilinx Virtex FPGA
chips and applied it to the
English-pronunciation-reasoning (EPR) task. The
evolvable reasoning hardware for the EPR task was
implemented with 270K gates, achieving an extremely
high reasoning speed of less than 300 ns/phoneme. It
also achieved a reasoning accuracy of 82.1% which is
almost the same accuracy as NETTalk in neural networks
and MBRTalk in parallel AI.},
added-at = {2008-06-19T17:35:00.000+0200},
author = {Yasunaga, Moritoshi and Kim, Jung Hwan and Yoshihara, Ikuo},
biburl = {https://www.bibsonomy.org/bibtex/2717e2a28f6b3d1318a20c1fe6356d40d/brazovayeye},
doi = {doi:10.1023/A:1011939025340},
interhash = {c49257bc9de5d9b5a4d378a5938778aa},
intrahash = {717e2a28f6b3d1318a20c1fe6356d40d},
issn = {1389-2576},
journal = {Genetic Programming and Evolvable Machines},
keywords = {FPGA, MBRTalk NETTalk, VLSI algorithms, design evolvable genetic hardware, methodology, reasoning,},
month = {September},
notes = {Article ID: 357592},
number = 3,
pages = {211--230},
timestamp = {2008-06-19T17:54:51.000+0200},
title = {Evolvable Reasoning Hardware: Its Prototyping and
Performance Evaluation},
volume = 2,
year = 2001
}