Abstract
In this chapter it is described the implementation of an artificial neural network in a reconfigurable parallel computer architecture using FPGA’s, named Reconfigurable Orthogonal Memory Multiprocessor (REOMP), which uses p 2 memory modules connected to p reconfigurable processors, in row access mode, and column access mode. It is described an alternative model of the neural network Neocognitron; the REOMP architecture, and the case study of alternative Neocognitron mapping; the performance analysis considering the computer systems varying the number of processors from 1 to 64; the applications; and the conclusions.
This is a preview of subscription content, log in via an institution to check access.
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
Arantes, M., Ide, A. N., and Saito, J. H. A System for Fingerprint Minutiae Classification and Recognition. volume 5, pages 2474–2478. Proceedings of the 9th International Conference on Neural Information Processing-ICONIP’2002. Singapura, 2002.
Bianchini, A. R. Arquitetura de Redes Neurais para o Reconhecimento Facial Baseado no Neocognitron. Master’s thesis, Universidade Federal de São Carlos.
T. J. Callahan, J. R. Hauser, and J. Wawrzyneck. The Garp Architecture and C Compiler. volume 33, pages 62–69. IEEE Computer Society, Computer: Innovative Technology for Computer Professionals, April 2002.
A. Dehon. Reconfigurable Architecture for General Purpose Computing. PhD thesis, Massachussets Institute of Technology (MIT), 1996.
A. Dehon. The Density Advantage of Configurable Computing. volume 33. IEEE Computer, 2000.
K. Fukushima. Neural-Network Model for a Mechanism of Pattern Recognition Unaffected by Shift in Position-Neocognitron. volume 62-A. Transactions of the IECE, 1979. Japan.
K. Fukushima and S. Miyake. Neocognitron: A New Algorithm for Pattern Recognition Tolerant of Deformations and Shift in Position. volume 15, pages 455–469. Pattern Recognition, 1982.
K. Fukushima and M. Tanigawa. Use of Different Thresholds in Learning and Recognition. volume 11, pages 1–17. Neurocomputing, 1996.
K. Fukushima and N. Wake. Improved Neocognitron with Bend-D detecting Cells. Proceedings of the IEEE-International Joint Conference on Neural Networks, 1992. Baltimore, Maryland.
S. C. Goldstein, H. Schmit, M. Budiu, S. Cadambi, M. Moe, and R. R. Taylor. Piperench: A Reconfigurable Architecture and Compiler. volume 33, pages 70–77, Issue 4. IEEE Computer, April 2000.
S. C. Goldstein, H. Schmit, M. Moe, M. Budiu, S. Cadambi, R. R. Taylor, and R. Laufer. Piperench: A Coprocessor for Streaming Multimedia Acceleration. pages 28–39. Proceedings of the 26th. Annual International Symposium on Computer Architecture (ISCA’99), 1999.
S. Hauck, T. W. Fry, M. M. Hosler, and J. P. Kao. The Chimaera Reconfigurable Functional Unit. pages 87–96. Proceedings of the IEEE Symposium on Field-Programmable Custom Computing Machines (FCCM’97), April 1997.
J. R. Hauser and J. Wawrzynek. Garp: A MIPS Processor with a Reconfigurable Coprocessor. Proceedings of the IEEE Symposium on Field-Programmable Custom Computing Machines-FCCM’ 97, April 1997. USA.
D. H. Hubel and T. N.Wiesel. Receptive Fields and Functional Architecture of Monkey Striate Cortex. volume 165, pages 215–243. J. Physiology, 1968.
K. Hwang, P. Tseng, and D. Kim. An Orthogonal Multiprocessor for Parallel Scientific Computations. volume 38, Issue 1, pages 47–61. IEEE Transactions On Computers, January, 1989.
A. N. Ide and J. H. Saito. A Reconfigurable Computer REOMP. volume 13, pages 62–69. Proceedings of the 13th Symposium on Computer Architecture and High Performance Computing-SBAC-PAD’2001, September 2001. Pirenópolis.
G. Lu. Modeling, Implementation and Scalability of the MorphoSys Dynamically Reconfigurable Computing Architecture. PhD thesis, Electrical and Computer Engineering Department, University of California, 2000. Irvine.
E. A. Mirsky. Coarse-Grain Reconfigurable Computing. PhD thesis, Massachussetts Institute of Technology, June 1996.
J. H. Saito. A Vector Orthogonal Multiprocessor NEOMP and Its Use in Neural Network Mapping. volume 11. Proceedings of the SBACPAD’ 99–11th Symposium on Computer Architecture and High Performance Computing, 1999. Natal, RN, Brazil.
H. Singh. Reconfigurable Architectures for Multimedia and Parallel Application Domains. PhD thesis, Electrical and Computer Engineering Department, University of California, 2000. Irvine.
H. Singh, M. Lee, G. Lu, F. Kurdahi, N. Bagherzadeh, and E. M. C. Filho. Morphosys: An Integrated Reconfigurable System for Data-Parallel and Computation-Intensive Applications. volume 49, pages 465–481. IEEE Transactions on Computers, May 2000.
M. J. Wirthlin and B. I. Hutchings. A Dynamic Instruction Set Computer. Proceedings of the IEEE Symposium on FPGA’s for Custom Computing Machines, April 1995.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2006 Springer
About this chapter
Cite this chapter
Ide, A.N., Saito, J.H. (2006). FPGA Implementations of Neocognitrons. In: Omondi, A.R., Rajapakse, J.C. (eds) FPGA Implementations of Neural Networks. Springer, Boston, MA . https://doi.org/10.1007/0-387-28487-7_7
Download citation
DOI: https://doi.org/10.1007/0-387-28487-7_7
Publisher Name: Springer, Boston, MA
Print ISBN: 978-0-387-28485-9
Online ISBN: 978-0-387-28487-3
eBook Packages: EngineeringEngineering (R0)