Abstract
This paper describes a new learning by example mechanism and its application for digital circuit design automation. This mechanism uses finite state machines to represent the inferred models or designs. The resultant models are easy to be implemented in hardware using current VLSI technologies. Our simulation results show that it is often possible to infer a well-defined deterministic model or design from just one sequence of examples. In addition this mechanism is able to handle sequential task involving long-term dependence. This new learning by example mechanism is used as a design by example system for automatic synthesis of digital circuits. Such systems have not previously been successfully developed mainly because of the lack of mechanism to implement them. From artificial neural network research, it seems possible to apply the knowledge gained from learning by example to form a design by example system. However, one of the problems with neural network approaches is that the resultant models are very difficult to be implemented in hardware using current VLSI technologies. By using the mechanism described in this paper, the resultant models are finite state machines that are well suited for digital designs. Several sequential circuit design examples are simulated and tested. Although our test results show that such a system is feasible for designing simple circuits or small-scale circuit modules, the feasibility of such a system for large-scale circuit design remains to be showed. Both the learning mechanism and the design method show potential and the future research directions are provided.
Similar content being viewed by others
References
P. Frasconi, M. Giro, M. Maggini, and G. Soda, “Unified integration of explicit knowledge and learning by example in recurrent networks,” IEEE Transactions on Knowledge and Data Engineering, vol. 7, no. 2, pp. 340–346, 1995.
A. Blum and A. Kalai, “Note on learning from multiple-instance examples,” Machine Learning, vol. 30, no. 1, pp. 23–29, 1998.
I. Pitas, E. Milios, and A.N. Venetsanopoulos, “A minimum entropy approach to rule learning from examples,” IEEE Transactions on Systems, Man and Cybernetics, vol. 22, no. 4, pp. 621–635, 1992.
S.P. Eberhardt, R. Tawel, T.X. Brown, T. Daud, and A.P. Thakoor, “Analog VLSI neural networks—implementation issues and examples in optimization and supervised learning,” IEEE Transactions on Industrial Electronics, vol. 39, no. 6, pp. 552–564, 1992.
O.Vermesan, “Amodular VLSI architecture for neural networks implementation,” From Natural to Artificial Neural Computation, vol. 930, pp. 794–799, 1995.
S. Espejo, R. Carmona, R. DominguezCastro, and A. RodriguezVazquez, “A CNN universal chip in CMOS technology,” International Journal on Circuit Theory and Applications, vol. 24, no. 1, pp. 93–109, 1996.
Proceedings of the 1998 Symposium on VLSI Technology Source, Symposium on VLSI Technology (sponsored by IEEE), 1998.
A. Moini, K. Eshraghian, and A. Bouzerdoum, “Impact of VLSI technology on neural networks,” IEEE International Conference on Neural Networks, pp. 158–163, 1995.
D.E. Rumelhart, G.E. Hinton, and R.J.Willians, “Learning internal representations by error propagation,” Parallel Distributed Processing, vol. 1, 1987.
R. Hecht-Nielsen, Neurocomputing, Addison-Wesley: Reading, MA, 1990.
T. Khanna, Foundations of Neural Networks, Addison-Wesley: Reading, MA, 1990.
H.C. Anderson, “Neural network machines,” IEEE Potentials, pp. 13–16, Feb. 1989.
J.B. Pollack, “Connectionism: Past, present, and future,” Artifi-cial Intelligence Review, vol. 3, pp. 3–22, 1989.
N.J. Nilsson, The Mathematical Foundations of Learning Machines, Morgan Kaufmann Publishers: San Mateo, CA, 1990.
S. Bibyk and M. Ismail, “Issues in analog VLSI and MOS techniques for neural computing,” in Analog VLSI Implementation of Neural systems, edited by C. Mead and M. Ismail, Kluwer Academic Publishers, pp. 103–133, 1989.
J. Hootman, (Ed.), IEEE Micro, Special Issue on Silicon Neural Networks, Dec., 1989.
C. Mead, Analog VLSI and Neural Systems, Addison-Wesley: Reading, MA, 1989.
C. Mead and M. Ismail, Analog VLSI Implementation of Neural Systems, Kluwer Academic Publishers: Boston, 1989.
M. Ismail and T. Fiez, Analog VLSI Signal and Information Processing, McGraw-Hill: New York, 1994.
H.C. Card, D.K. McNeill, and C.R. Schneider, “Analog VLSI circuits for competitive learning networks,” Analog Integrated Circuits and Signal Processing, vol. 15, no. 3, pp. 291–314, 1998.
P.S. Eberhardt, R. Tawel, T.X. Brown, T. Daud, and A.P. Thakoor, “Analog VLSI neural networks: Implementation issues and examples in optimization and supervised learning,” IEEE Transactions on Industrial Electronics, vol. 39, no. 6, pp. 522–564, 1992.
M.W. Roth, “Survey of neural network technology for automatic target recognition,” IEEE Transactions on Neural Networks, vol. 1, no.1, pp. 28–43, 1990.
C.L. Giles, G.M. Kuhn, and R.J. Williams (Guest Editors), “Special issue on dynamic recurrent neural networks, IEEE Transactions on Neural Networks, vol. 5, no. 2, 1994.
M.I. Jordan, “Attractor dynamics and parallelism in connectionist sequential machine,” in Proceedings of the Eighth Annual Conference of the Cognitive Science Society, pp. 521–545, 1986.
Y. Bengio, P. Frasconi, and P. Simard, “The problem of learning long-term dependencies in recurrent networks,” in IEEE International Conference on Neural Networks, 1993.
Y. Bengio, P. Simard, and P. Frasconi, “Learning long-term dependencies with gradient descent is difficult,” IEEE Transactions on Neural Networks, vol. 5, no. 2, 1994.
K.J. Breeding, Digital Design Fundamentals, Prentice Hall: Englewood Cliffs, NJ, 1992.
K.C. Chang, Digital Systems Design with VHDL and Synthesis: An Integrated Approach, IEEE Computer Society: Los Alamitos, CA, 1999.
H. Dicken and M. Griffith (Eds.), ASIC Outlook, 1998: An Application Specific IC Report and Directory, Integrated Circuit Engineering Corporation, Nov. 1997.
S. Porat and J.A. Feldman, “Learning automata from ordered examples,” in Proceedings of the 1988 Workshop on Computational Learning Theory (also on Machine Learning, 1991), 1988.
I. Rouvellou and G.W. Hart, “Inference of a probabilistic finite state machine from its output,” IEEE Transactions on Systems, Man, and Cybernetics, vol. 25, no. 3, pp. 424–437, 1995.
A.W. Biermann and J.A. Feldman, “On the synthesis of finitestate machines from samples of their behavior,” IEEE Transactions on Computers, vol. 21, pp. 592–597, 1972.
B.J. Oommen, N. Andrade, and S. Iyengar, “Trajectory planning of robot manipulators in noisy work spaces using stochastic automata,” International Journal of Robotics Research, vol. 10, no. 2, pp. 135–148, 1991.
A.C. Barto and P. Anandan, “Pattern-recognizing stochastic learning automata,” IEEE Transactions on Systems, Man, and Cybernetics, vol. SMC-15, no. 3, pp. 360–375, 1985.
K. Lanctot and B.J. Oommen, “Discretized estimator learning automata,” IEEE Transactions on Systems, Man, and Cybernetics, vol. 22, no. 6, 1992.
R.L. Rivest and R.E. Schapire, “Inference of finite automata using homing sequences,” in Proceedings of the Twenty First Annual ACM Symposium on Theory of Computing, May 15–17, pp. 411–420, 1989.
D. Angluin, “Learning regular sets from queries and counter examples,” Information and Computation, vol. 75, pp. 87–106, 1987.
D. Angluin, “A note on the number of queries needed to identify regular languages,” Information and Control, 1981.
O.H. Ibarra and T. Jiang, “Learning regular languages from counterexamples,” in Proceedings of the 1988 Workshop on Computational Learning Theory, 1988.
A. Marron, “Learning pattern languages form a single initial example and from queries,” in Proceedings of the 1988 Workshop on Computational Learning Theory, 1988.
E.M. Gold, “System identification via state characterization,” Automatica, 1972.
L.A. Litteral, “An algorithm for solving the sequential machine identification problem,” Thesis, The Ohio State University, 1973.
Z.Kohavi, Switching and Finite Automata Theory,McGraw-Hill Book Company: New York, 1978.
R.E. Schapire, “Diversity-based inference of finite automata,” MIT/LCS/TR-414, 1988.
M.C. Mozer and J. Bachrach, “SLUG: A connectionist architecture for inferring the structure of finite-state environments,” Machine Learning, vol. 7, pp. 139–160, 1991.
B. Choi, “Automata for learning sequential tasks,” New Generation Computing, vol. 16, pp. 23–54, 1998.
A. Grasselliand and F. Luccio, “A method for minimizing the number of internal states in incompletely specified sequential networks,” IEEE Transactions on Electronic Computers, vol. 14, no. 3, pp. 350–359, 1965.
W.S. Meisel, “A note on internal state minimization in incompletely specified sequential networks,” IEEE Transactions on Electronic Computers, pp. 508–509, 1967.
E.M. Gold, “Complexity of automaton identification from given data,” Information and Control, vol. 37, pp. 306–320, 1978.
L. Pitt and M.K.Warmuth, “The minimum consistent DFAproblem cannot be approximated within any polynomial,” in Proceedings of the 21 Annual ACM Symposium on Theory of Computing, pp. 421–432, 1989.
R. Alur and D.L. Dill, “Theory of timed automata,” Theoretical Computer Science, vol. 126, no. 2, pp. 183–235, 1994.
C. Largouët and M.O. Cordier, “Timed automata model to improve the classification of a sequence of images,” in Proc. of 14th European Conference on Artificial Intelligence (ECAI' 2000), 2000, pp. 156–160.
A. Puri, “Undecidable problem for timed automat,” Discrete Event Dynamic Systems: Theory and Applications, vol. 9, no. 2, pp. 135–146, 1999.
R. Alur, R.P. Kurshan, and M. Viswanatha, “Membership questions for timed and hybrid automata,” in Proceedings of Real-Time Systems Symposium, 1998, pp. 254–263.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Choi, B. Applying Learning by Examples for Digital Design Automation. Applied Intelligence 16, 205–221 (2002). https://doi.org/10.1023/A:1014338000161
Issue Date:
DOI: https://doi.org/10.1023/A:1014338000161