Abstract
An artificial neural network (ANN) is a parallel distribution of linear processing units arranged as layers. Parallelism, modularity and dynamic adaptation are computational characteristics associated with networks. These characteristics support FPGA implementation of networks, because parallelism takes advantage of FPGA concurrency, and modularity and dynamic adaptation benefit from network reconfiguration. The most important aspects of FPGA implementation of neural networks are: the benefits of reconfiguration, the representation of internal data and implementation issues like weight precision and transfer functions. This paper proposes a number of internal data formats that optimize the network precision and a way of implementing sigmoid transfer functions to make the most of FPGA implementation.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Kopacek, P.: Advances in Robotics. In: Proc. of 10th Int. Workshop on Computer Aided Systems Theory, pp. 272–274 (2005)
De Lope, J., Maravall, D.: A biomimetic approach for the stability of biped robots. In: Proc. of 5th Int. Conf. on Climbing and Walking Robots (2004)
De Lope, J., González-Careaga, R., Zarraonandia, T., Maravall, D.: Inverse kinematics for humanoid robots using artificial neural networks. In: Moreno-Díaz Jr., R., Pichler, F. (eds.) EUROCAST 2003. LNCS, vol. 2809, pp. 448–459. Springer, Heidelberg (2003)
De Lope, J., Zarraonandia, T., González-Careaga, R., Maravall, D.: Solving the inverse kinematics in humanoid robots: A neural approach. In: Mira, J., Álvarez, J.R. (eds.) IWANN 2003. LNCS, vol. 2687, pp. 177–184. Springer, Heidelberg (2003)
Cox, C.E., Blanz, E.: Ganglion — A fast field-programmable gate array implementation of a connectionist classifier. IEEE J. of Solid-State Circuits 28, 288–299 (1992)
Eldredge, J.G., Hutchings, B.L.: Density of enhancement of a neural network using FPGAs and run-time reconfiguration. In: Proc. of IEEE Workshop on Field-Programmable Custom Computing Machines, pp. 180–188 (1994)
Eldredge, J.G., Hutchings, B.L.: RRANN: A hardware implementation of the back-propagation algorithm using reconfigurable FPGAs. In: Proc. of IEEE Int. Conf. on Neural Networks, pp. 2097–2102 (1994)
James-Roxby, P.: Adapting constant multipliers in a neural network implementation. In: Proc. of IEEE Symposium on Field-Programable Custom Computing Machines, pp. 335–336 (2000)
Pérez-Uribe, A., Sánchez, E.: FPGA implementation of an adaptable-size neural network. In: Vorbrüggen, J.C., von Seelen, W., Sendhoff, B. (eds.) ICANN 1996. LNCS, vol. 1112, pp. 382–388. Springer, Heidelberg (1996)
Marchesi, M., Orlandini, G., Piezza, F., Uncini, A.: Fast neural networks without multipliers. IEEE Trans. on Neural Networks 4, 53–62 (1993)
Nichols, K.R., Moussa, M.A., Areibi, S.M.: Feasibility of floating-point arithmetic in FPGA based artificial neural networks. In: Proc. of 15th Int. Conf. on Computer Applications in Industry and Engineering, pp. 8–13 (2002)
Wolf, D.F., Romero, R.A.F., Marques, E.: Using embedded processors in hardware models of artificial neural networks. In: Proc. do Simposio Brasileiro de Automatao Inteligente, pp. 78–83 (2001)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2005 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Prieto, B., de Lope, J., Maravall, D. (2005). Reconfigurable Hardware Implementation of Neural Networks for Humanoid Locomotion. In: Mira, J., Álvarez, J.R. (eds) Artificial Intelligence and Knowledge Engineering Applications: A Bioinspired Approach. IWINAC 2005. Lecture Notes in Computer Science, vol 3562. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11499305_41
Download citation
DOI: https://doi.org/10.1007/11499305_41
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-26319-7
Online ISBN: 978-3-540-31673-2
eBook Packages: Computer ScienceComputer Science (R0)