Abstract
Providing machine learning capabilities on low cost electronic devices is a challenging goal especially in the context of the Internet of Things paradigm. In order to deliver high performance machine intelligence on low power devices, suitable hardware accelerators have to be introduced. In this paper, we developed a method enabling to evolve a hardware implementation together with a corresponding software controller for key components of smart embedded systems. The proposed approach is based on a multi-objective design space exploration conducted by means of extended linear genetic programming. The approach was evaluated in the task of approximate sigmoid function design which is an important component of hardware implementations of neural networks. During these experiments, we automatically re-discovered some approximate sigmoid functions known from the literature. The method was implemented as an extension of an existing platform supporting concurrent evolution of hardware and software of embedded systems.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Amin, H., Curtis, K.M., Hayes-Gill, B.R.: Piecewise linear approximation applied to nonlinear function of a neural network. IEE Proc. Circ. Dev. Syst. 144(6), 313–317 (1997)
Brameier, M., Banzhaf, W.: Linear Genetic Programming. Springer, Berlin (2007)
Cheang, S.M., Leung, K.S., Lee, K.H.: Genetic parallel programming: design and implementation. Evol. Comput. 14(2), 129–156 (2006)
Deniziak, S., Gorski, A.: Hardware/software co-synthesis of distributed embedded systems using genetic programming. In: Hornby, G.S., Sekanina, L., Haddow, P.C. (eds.) ICES 2008. LNCS, vol. 5216, pp. 83–93. Springer, Heidelberg (2008). doi:10.1007/978-3-540-85857-7_8
Dick, R.P., Jha, N.K.: MOGAC: a multiobjective genetic algorithm for hardware-software cosynthesis of distributed embedded systems. IEEE Trans. CAD Integr. Circ. Syst. 17(10), 920–935 (1998)
Koza, J.R.: Genetic Programming II: Automatic Discovery of Reusable Programs. MIT Press, Cambridge (1994)
Leung, K.S., Lee, K.H., Cheang, S.M.: Parallel programs are more evolvable than sequential programs. In: Ryan, C., Soule, T., Keijzer, M., Tsang, E., Poli, R., Costa, E. (eds.) EuroGP 2003. LNCS, vol. 2610, pp. 107–118. Springer, Heidelberg (2003). doi:10.1007/3-540-36599-0_10
McCluskey, E.J.: Minimization of Boolean functions. Bell Syst. Tech. J. 35(6), 1417–1444 (1956)
Minarik, M., Sekanina, L.: Concurrent evolution of hardware and software for application-specific microprogrammed systems. In: 2013 IEEE International Conference on Evolvable Systems (ICES), pp. 43–50 (2013). Proceedings of the 2013 IEEE Symposium Series on Computational Intelligence (SSCI). IEEE Computational Intelligence Society
Minarik, M., Sekanina, L.: Exploring the search space of hardware/software embedded systems by means of GP. In: Nicolau, M., Krawiec, K., Heywood, M.I., Castelli, M., GarcÃa-Sánchez, P., Merelo, J.J., Rivas Santos, V.M., Sim, K. (eds.) EuroGP 2014. LNCS, vol. 8599, pp. 112–123. Springer, Heidelberg (2014). doi:10.1007/978-3-662-44303-3_10
Misra, J., Saha, I.: Artificial neural networks in hardware: a survey of two decades of progress. Neurocomputing 74(1–3), 239–255 (2010)
Parhami, B.: Computer Arithmetic: Algorithms and Hardware Designs. Oxford University Press, Oxford (2000)
Poli, R., Langdon, W.B.: Sub-machine-code genetic programming. In: Advances in Genetic Programming, pp. 301–323. MIT Press, Cambridge (1999)
Shang, L., Dick, R.P., Jha, N.K.: SLOPES: hardware-software cosynthesis of low-power real-time distributed embedded systems with dynamically reconfigurable FPGAs. IEEE Trans. CAD Integr. Circ. Syst. 26(3), 508–526 (2007)
Tempesti, G., Mudry, P.A., Zufferey, G.: Hardware/software coevolution of genome programs and cellular processors. In: First NASA/ESA Conference on Adaptive Hardware and Systems (AHS 2006), pp. 129–136. IEEE Computer Society (2006)
Tommiska, M.T.: Efficient digital implementation of the sigmoid function for reprogrammable logic. IEE Proc. Comput. Digital Tech. 150(6), 403–411 (2003)
Üçoluk, G.: Genetic algorithm solution of the TSP avoiding special crossover and mutation. In: Sixth Turkish AI and NN Symposium (TAINN VI), Ankara, pp. 57–62 (1997)
Zhang, M., Vassiliadis, S., Delgado-Frias, J.G.: Sigmoid generators for neural computing using piecewise approximations. IEEE Trans. Comput. 45(9), 1045–1049 (1996)
Acknowledgments
This work was supported by the Czech science foundation project GA16-17538S.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this paper
Cite this paper
Minarik, M., Sekanina, L. (2017). On Evolutionary Approximation of Sigmoid Function for HW/SW Embedded Systems. In: McDermott, J., Castelli, M., Sekanina, L., Haasdijk, E., GarcÃa-Sánchez, P. (eds) Genetic Programming. EuroGP 2017. Lecture Notes in Computer Science(), vol 10196. Springer, Cham. https://doi.org/10.1007/978-3-319-55696-3_22
Download citation
DOI: https://doi.org/10.1007/978-3-319-55696-3_22
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-55695-6
Online ISBN: 978-3-319-55696-3
eBook Packages: Computer ScienceComputer Science (R0)