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.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
C. Stanfill and D. W altz, “Toward memory-based reasoning,” Commun. ACM vol.29(12), pp. 1213-1228, 1986.
H. Kitano (ed.), Massively Parallel Artificial Intelligence, AAAI Press/MIT Press: Cambridge, MA, 1994.
H. Kitano, “Challenges of massive parallelism-the Computers and Thought Award Lecture,” in Proc.13th Int.Joint Conf.Artificial Intelligence, Chambery, France, R. Bajcsy (ed.), Morgan Kaufmann: San Mateo, CA, 1993, pp. 813-834.
H. Kitano and T. Higuchi, “Massively parallel memory-based parsing,” in Proc.12th Int.Joint Conf. Artificial Intelligence, Sydney, Australia, J. Mylopoulos and R. Reiter (eds.), Morgan Kaufmann: San Mateo, CA, 1991, pp. 918-924.
F. Lombardi (Guest ed.), “Field-programmable gate array,” IEEE Design and Test of Computers January-March, pp. 8-50, 1998.
T.J. Sejnowski and C.R. Rosenberg, “Parallel networks that learn to pronounce English text,” Complex Syst. vol. 1, pp. 145-168, 1987.
K. Fukunaga, Introduction to Statistical Pattern Recognition, Academic Press: San Diego, CA, 1990.
C. Bishop, Neural Networks for Pattern Recognition, Oxford Press, 1995.
S.B.Nikola, “Simulating artificial neural networks on parallel architectures,” IEEE Computer, vol. 29(3), pp. 56-63, 1996.
M. Yasunaga and H. Kitano, “Robustness of the memory-based reasoning implemented by wafer scale integration,” IEICE (Institute of Electronics Information and Communication Engineering Japan) Trans.Information and Syst. vol.E76-D(3), pp. 336-344, 1993.
Y. Sato, K. Shibata, M. Asai, M. Ohki, M. Sugie, T. Sakaguchi, M. Hashimoto, and Y.Kuwahara, “Development of a high-performance general purpose neuro-computer composed of 512 digital neurons,” in Proc.IEEE Int.Joint Conf.Neural Networks (IJCNN'93), Nagoya, Japan, 1993, pp. 1967-1970.
M. Yasunaga and T. Ochiai, “Performance evaluation of neural network hardware using time-shared bus and integer representation architecture,” IEICE (Institute of Electronics Information and Communication Engineering Japan) Trans.Information and Syst.vol. E79-D(6), pp. 888-896, 1996.
M. Yasunaga, A. Yamada, and T. Ochiai, “Performance of a bus-based parallel computer with integer-representation processors applied to artificial neural network and parallel AI domains,” in Proc.IEEE Int.Conf.Knowledge-Based Intelligent Electronic Systems (KES'98), Adelaide, South Australia, L.C. Jain and R.K. Jain (eds.), 1998, pp. 519-527.
T.A. Brown, Genomes, BIOS Scientific Publishers Ltd., 1999.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Yasunaga, M., Kim, J.H. & Yoshihara, I. Evolvable Reasoning Hardware: Its Prototyping and Performance Evaluation. Genetic Programming and Evolvable Machines 2, 211–230 (2001). https://doi.org/10.1023/A:1011939025340
Issue Date:
DOI: https://doi.org/10.1023/A:1011939025340