Abstract
To achieve intelligent real-time processing, the paper presents a weightless neural-based cognitive system which is capable of classifying, analysing, and prediction from sight or sound. The proposed cognitive system fused recursive-least-square (RLS) filters in parallel with an enhanced probabilistic convergent network (EPCN) serially—implemented on field programmable gate array. The novelty is that EPCN does not require an optimum result from RLS to achieve good responses from the RLS–EPCN fusion, thereby further offering two main distinguishing features: compactness and speed. Test results demonstrate RLS–EPCN’s suitability to exploration/exploitation of hostile surroundings such as sea exploration.
Similar content being viewed by others
References
De Carvalho ACPLF, Fairhurst MC, Bisset DL (1998) Combinig two boolean networks for image classification. In: Austin J (ed) RAM-based NNs. World Scientific, Singapore
O’Keefe SEM, Austin J (1998) Content analysis of document images using the ADAM associative memory. In: Austin J (ed) RAM-based NNs. World Scientific, Singapore
Bledsoe WW, Browning I (1959) Pattern recognition and reading by machine. In: proceedings of Joint Comp. Conference, pp 232–255
Aleksander I, Thomas WV, Bowden PA (1984) WISARD: a radical step forward in image recognition. Sens Rev 4(3):120–124
Austin J (ed) (1998) RAM-based neural networks. World Scientific Publishing Co., Inc., River Edge, NJ. ISBN: 9810232535
Howells GJ, Fairhurst MC, Bisset DL (1995) PCN: the probabilistic convergent network, electronics engineering laboratories. University of Kent, Canterbury
Sirlantis K, Howells G, Gherman B (2009) Novel modular weightless neural architecture for biometric-based recognition. In: 17th Symposium On ANN, ESANN, Bruges, Belgium April 2009
Lorrentz P, Howells WGH, McDonald-Maier KD (2009) FPGA based EPCN for human iris recognition. In: 17th Symposium On ANN, ESANN, Bruges, Belgium
De Oliveira W (2009) Quantum RAM-based neuralnNetworks. In: 17th Symposium On ANN, ESANN, Bruges, Belgium
Amdahl GM (1967) Validity of the single processor approach to achieving large scale computing capabilities. In: AFIPS spring joint computer conference, IBM Sunnyvale California, USA
Hill MD, Marty MR (2008) Amdahl’s Law in the Multicore Era, IEEE Computer Society, July 2008
Lorenzo L, Antonello R (2013) The graph matching problem. Pattern Analysis and Application 16:253–283. doi:10.1007/s10044-012-0284-8 Springer-Verlag London Limited
Tomasz K, Wojciech I, Przemyslaw K (2012) MapReduce approach to relational influence propagation in complex networks; Pattern Analysis and Application, doi 10.1007/s10044-012-0294-6; Springer, September 2012
Commuri S, Li Y, Hougen D, Fierro R (2004) Evaluating intelligence in unmanned ground vehicle teams, performance metrics for intelligent systems workshop (PerMIS’04). NIST, Gaithersburg
Botelho SSC, Simões EV, Uebel LF, Barone DAC (1996) High speed neural control for robot navigation. In: IEEE International Conference on systems, man, and cybernetics. Beijing, pp 421–429
Shang L, Yi Z, Ji L (2007) Binary Image thinning using autowaves generated by PCNN. Neural Process Lett 25:49–62
Chalfant EC, Lee S (1999) Measuring the Intelligence of robotic systems: an engineering perspective. In: Proceedings of International Symposium on Intelligent Systems, Gaithersburg
Spaanenburg L, Alberts R, Slump CH, Van der Zwaag BJ (2003) Natural learning of NNs by reconfiguration. In: Rodriguez-Vazquez A, Abbott D, Carmona R (eds.) SPIE International Symposium On Microtechnologies for the new Millennium, vol. 5119. (Maspalomas, Gran Canaria, Spain), pp 273–284
Simões EV, Uebel LF, Barone DAC (1996) Hardware implementation of RAM neuralnNetworks. Pattern Recognit Lett 17:421–429
Freeman M, Austin J (2005) Designing a binary NN co-processor, Digital System Design, 2005. In: Proceedings of 8th Euromicro Conference on Digital System Design Digital Object Identifier 10.1109/DSD.2005.34, pp 223–226
Lorrentz P, Howells WGH, McDonald-Maier KD (2006) EPCN. In: Proceedings of the 6th International Conference on Recent Advances in Soft Computing (RASC 2006), pp 267–272
Embree P (1995) C Algorithms for Real-time DSP (Digital Signal Processing). Prentice Hall PTR, Upper Sadle River
Hannan Bin Azhar MA, Dimond KR (2002) Design of an FPGA based adaptive neural controller for intelligent robot navigation Digital System design. In: Proceedings of Euromicro Synposium
Kennedy JV, Austin J, Pack R, Cass B (1995) C-NNAP: A dedicated processor for binary neuralnNetworks. In: the proceedings of the International Conference on Neural Networks ‘95
Proakis John G (2001) Digital communication, 4th edn. The Mcgraw-Hill Companies, Inc., New York, NY
Xilinx University Program Virtex-II Pro Development System (2005) Hardware Reference Manual, UG069, March 2005
Gingras DF (1994) North Elba Trial Summary, SACLANT Undersea Research Centre, SM-121, La Spezia, Italy. August 1994
Jesus SM (1993) Broadband matched-field processing of transient signals in shallow water. J Acoust Soc Am 93(4):1841–1850
Ellis DD, Gerstoft P (1996) Using inversion techniques to extract bottom scattering strengths and sound speeds from shallow water reverberation data. In: 3rd EU conference on Underwater Acoustics, Heraklion, crete, Greece. June 1996
Kim S et al (2001) Spatial resolution of time-reversal arrays in shallow water. J Acoust Soc Am 110(2):820–829
Lorrentz P, Howells WGJ, McDonald-Maier KD (2008) An FPGA based adaptive weightless Neural Network Hardware, IEEE, NASA/ESA—2008, AHS-2008
Coric S, Latinovic I, Pavasovic A (2000) A NN FPGA Implementation: issues and applications, NEUREL-2000, Yugoslavia, sept. 25-27
Muthuramalingam A, Himavathi S, Srinivasan E (2007) Neural network implementation using FPGA: issues and application. Int J Inf Technol 4(2):86–92
Khan FM, Arnold MG, Pottenger WM (2005) Hardware-based Support Vector Machine Classification in Logarithmic Number System, (2005). In: IEEE Symposium on Circuit and Systems (ISCAS), May 2005
Patra JC, Devi TA, Meher PK (2007) RBF Implementation of Intelligent Pressure Sensor on Field Programmable Gate Arrays, ICICS
Acknowledgments
Thanks to: SACLANT ASW Research Centre, La Spezia, Italy, for SONAR databases.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Lorrentz, P. The FPGA-based multi-classifier. Pattern Anal Applic 18, 207–223 (2015). https://doi.org/10.1007/s10044-014-0380-z
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10044-014-0380-z