Abstract
This paper investigates the use of a network of cascaded Field Programmable Analogue Arrays (FPAAs) to implement an evolved, analogue, Spiking Neural Network (SNN) pole balance controller. The SNN hardware platform interfaces to a simulated pole balancing model for evaluation. Performance of the evolved analogue hardware controller is compared to that of a software-based SNN controller. The evolved hardware network displays an improved tolerance to changing environments compared with networks evolved solely in simulation. The paper goes on to discuss the suitability of low density FPAA devices for analogue-centric hardware neural network platforms. It concludes by outlining some possible directions which address the observed limitations of using FPAAs for ANNs.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Hohmann, S., Schemmel, J., Schurmann, F., Meier, K.: Exploring the parameter space of a genetic algorithm for training an analog neural network. In: Langdon, W.B., Cantu-Paz, E., Mathias, K., et al. (eds.) Proceedings of the Genetic and Evolutionary Computation Conference (GECCO 2002), pp. 375–382 (2002)
Schemmel, J., Gruebl, A., Meier, K., Mueller, E.: Implementing Synaptic Plasticity in a VLSI Spiking Neural Network Model. In: Proceedings of the 2006 International Joint Conference on Neural Networks (IJCNN 2006). IEEE Press, Orlando (2006)
Schemmel, J., Meier, K., Mueller, E.: A new VLSI model of neural microcircuits including spike time dependent plasticity. In: Proceedings of IEEE International Joint Conference on Neural Networks, vol. 3 (2004)
Schemmel, J., Meier, K., Schürmann, F.: A VLSI Implementation of an Analog Neural Network Suited for Genetic Algorithms. In: Proceedings of Evolvable Systems: From Biology to Hardware: 4th International Conference, ICES 2001, Tokyo, Japan, October 3-5 (2001)
Berenson, D., Estevez, N., Lipson, H.: Hardware Evolution of Analog Circuits for In-situ Robotic Fault-Recovery. Evolvable Hardware 2, 12–19
Dong, P., Bilbro, G., Chow, M.: Implementation of Artificial Neural Network for Real Time Applications Using Field Programmable Analog Arrays. In: International Joint Conference on Neural Networks, IJCNN 2006, pp. 1518–1524 (2006)
Terry, M., Marcus, J., Farrell, M., Aggarwal, V., O’Reilly, U.: GRACE: Generative Robust Analog Circuit Exploration. In: 9th European Conference on Genetic Programming, EVO-Workshops, EVOHOT track (2006)
Pasero, E., Perri, M.: Hw-Sw codesign of a flexible neural controller through a FPGA-based neural network programmed in VHDL. In: Proceedings of IEEE International Joint Conference on Neural Networks, vol. 4 (2004)
Pérez-Uribe, A., Sanchez, E.: Structure-Adaptable Neurocontrollers: A Hardware-Friendly Approach. Biological and Artificial Computation: From Neuroscience to Technology, 1251–1259
Kumagai, T., Wada, M., Hashimoto, R., Utsugi, A.: Dynamical control by recurrent neural networks through genetic algorithms. International Journal of Adaptive Control and Signal Processing 13(4), 261–271 (1999)
Ventresca, M., Ombuki, B.: Search Space Analysis of Recurrent Spiking and Continuous-time Neural Networks. In: International Joint Conference on Neural Networks, IJCNN 2006, pp. 4514–4521(2006)
Maher, J., Mc Ginley, B., Rocke, P., Morgan, F.: Intrinsic Hardware Evolution of Neural Networks in Reconfigurable Analogue and Digital Devices. In: Proceedings of the 14th Annual IEEE Symposium on Field-Programmable Custom Computing Machines (FCCM 2006), vol. 00, pp. 321–322 (2006)
Rocke, P., Maher, J., Morgan, F.: Platform for Intrinsic Evolution of Analogue Neural Networks. In: Proceedings of the 2005 International Conference on Reconfigurable Computing and FPGAs (ReConFig 2005) on Reconfigurable Computing and FPGAs (2005)
Rocke, P., McGinley, B., Morgan, F., Maher, J.: Reconfigurable Hardware Evolution Platform for a Spiking Neural Network Robotics Controller. In: Diniz, P.C., Marques, E., Bertels, K., Fernandes, M.M., Cardoso, J.M.P. (eds.) ARCS 2007. LNCS, vol. 4419, pp. 373–378. Springer, Heidelberg (2007)
Bellis, S., Mahmood, K., Saha, C., Delaney, K., O’Mathuna, C., Pounds-Cornish, A., de Souza, G., Colley, M., Hagras, H., Clarke, G., et al.: FPGA Implementation of Spiking Neural Networks-an Initial Step towards Building Tangible Collaborative Autonomous Agents. In: Proceedings of 2004 International Conference on Field Programmable Technology, ICFPT, vol. 4, pp. 6–8 (2004)
Field Programmable Analogue Arrays, http://www.anadigm.com
Maass, W.: Networks of spiking neurons: The third generation of neural network models. Neural Networks 10(9), 1659–1671 (1997)
Gerstner, W., Kistler, W.: Spiking neuron models (2002)
Holland, J.: Adaptation in natural and artificial systems. University of Michigan press (1975)
Plante, J., Shaw, H., Mickens, L., Johnson-Bey, C.: Overview of field programmable analog arrays as enabling technology for evolvable hardware for high reliability systems. In: Proceedings of 2003 NASA/DoD Conference on Evolvable Hardware, pp. 77–78 (2003)
Hereford, J., Pruitt, C.: Robust sensor systems using evolvable hardware. In: Proceedings of 2004 NASA/DoD Conference on Evolvable Hardware, pp. 161–168 (2004)
Amaral, J., Amaral, J., Santini, C., Tanscheit, R., Vellasco, M., Pacheco, M.: Towards evolvable analog artificial neural networks controllers. In: Proceedings of 2004 NASA/DoD Conference on Evolvable Hardware (2004)
Harkin, J., et al.: Novel Interconnect Strategy for Large Scale Implementations of NNs. IEEE Soft Comp. in Indust. App. (2007)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2008 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Rocke, P., McGinley, B., Maher, J., Morgan, F., Harkin, J. (2008). Investigating the Suitability of FPAAs for Evolved Hardware Spiking Neural Networks. In: Hornby, G.S., Sekanina, L., Haddow, P.C. (eds) Evolvable Systems: From Biology to Hardware. ICES 2008. Lecture Notes in Computer Science, vol 5216. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-85857-7_11
Download citation
DOI: https://doi.org/10.1007/978-3-540-85857-7_11
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-85856-0
Online ISBN: 978-3-540-85857-7
eBook Packages: Computer ScienceComputer Science (R0)