Hardware implementation methods in random vector functional-link networks

Applied Intelligence

Volumn 41, Issue 1, 2014, Pages 184-195

  Martínez Villena, José M ^a   Rosado Muñoz, Alfredo ^a   Soria Olivas, Emilio ^a  

^a UNIVERSITY OF VALENCIA   (Spain)

Author keywords

Embedded and real time systems; Fast learning; Matrix inversion; Neural network training; Random Vector Functional Link Networks; VHDL

Indexed keywords

CLASSIFICATION (OF INFORMATION); FEEDFORWARD NEURAL NETWORKS; FIXED POINT ARITHMETIC; INTERACTIVE COMPUTER SYSTEMS; MATRIX ALGEBRA; PERSONAL COMPUTERS; REAL TIME SYSTEMS;

EMBEDDED AND REAL-TIME SYSTEMS; FAST LEARNING; FUNCTIONAL-LINK NETWORK; MATRIX INVERSIONS; NEURAL NETWORK TRAINING; VHDL;

HARDWARE;

EID: 84904207987     PISSN: 0924669X     EISSN: None     Source Type: Journal    
DOI: 10.1007/s10489-013-0501-1     Document Type: Article

References (59)

1. Bishop CM (2006) Pattern recognition and machine learning. Springer, Berlin
2. Bjõrck A (1967) Solving linear least squares problems by Gram-Schmidt orthogonalization. BIT Numer Math 7:1-21
3. Bjõrck A (1996) Numerical methods for least squares problems. SIAM, Philadelphia
4. Carcenac M (2009) A modular neural network for super-resolution of human faces. Appl Intell 30(2):168-186. doi: 10.1007/s10489-007-0109-4
5. de Castro R, Araujo R, Cardoso J, Freitas D (2010) A new linear parametrization for peak friction coefficient estimation in real time. In: Vehicle power and propulsion conference (VPPC), 2010 IEEE, pp 1-6. doi: 10.1109/VPPC.2010.5729138
6. Chauvin Y, Rumelhart D (1995) Backpropagation: theory, architectures, and applications. Erlbaum, Hillsdale
7. Chen X, Dong ZY, Meng K, Xu Y, Wong KP, Ngan HW (2012) Electricity price forecasting with extreme learning machine and bootstrapping. IEEE Trans Power Syst 27(4):2055-2062. doi: 10.1109/TPWRS.2012.2190627
8. Cheney E, Kincaid D (2007) Numerical mathematics and computing, International student edn. Brooks/Cole, Belmont
9. Decherchi S, Gastaldo P, Dahiya R, Valle M, Zunino R (2011) Tactile-data classification of contact materials using computational intelligence. IEEE Trans Robot 27(3):635-639. doi: 10.1109/TRO.2011.2130030
10. Decherchi S, Gastaldo P, Leoncini A, Zunino R (2012) Efficient digital implementation of extreme learning machines for classification. IEEE Trans Circuits Syst II, Express Briefs 59(8):496-500. doi: 10.1109/TCSII.2012.2204112
11. Duan G, Huang Z, Wang J (2009) Extreme learning machine for bank clients classification. In: International conference on information management, innovation management and industrial engineering, vol 2, pp 496-499. doi: 10.1109/ICIII.2009.277
12. Ganchosov PN, Kuzmanov G, Kabakchiev H, Behar V, Romansky RP, Gaydadjiev GN (2009) FPGA implementation of modified Gram-Schmidt qr-decomposition. In: Proceedings of the 3rd HiPEAC workshop on reconfigurable computing, pp 41-51
13. Gander W (1980) Algorithms for the QR-decomposition. Research report no. 80-02 edn. Seminar Fuer Angewandte Mathematik, Eidgenoessische Technische Hochschule, Zurich
14. Geist G, Howell G, Watkins D (1999) The BR eigenvalue algorithm. SIAM J Matrix Anal Appl 20(4):1083-1098 (Pubitemid 129330059)
15. Gentle JE (2007) Matrix algebra: theory, computations, and applications in statistics, 1st edn. Springer, Berlin
16. Harrison D, Rubinfeld DL (1978) Hedonic prices and the demand for clean air. J Environ Econ Manag 5:81-102
17. Huang GB, Zhu QY, Siew CK (2006) Extreme learning machine: theory and applications. Neurocomputing 70(1-3):489-501. doi: 10.1016/j.neucom.2005.12.126. Neural networks - selected papers from the 7th Brazilian symposium on neural networks (SBRN'04), 7th Brazilian symposium on neural networks (Pubitemid 44615772)
18. Huang GB, Wang D, Lan Y (2011) Extreme learning machines: a survey. Int J Mach Learn Cybern 2:107-122. doi: 10.1007/s13042-011-0019-y
19. Igelnik B, Pao Y (1995) Stochastic choice of basis functions in adaptive function approximation and the functional-link net. IEEE Trans Neural Netw 6(6):1320-1329
20. Irturk A (2007) Implementation of QR decomposition algorithms using FPGA. Master's thesis, Department of Electrical and Computer Engineering, University of California, Santa Barbara
21. Irturk A, Benson B, Arfaee A, Kastner R (2008) Automatic generation of decomposition based matrix inversion architectures. In: International conference on ICECE technology, FPT 2008, pp 373-376. doi: 10.1109/FPT.2008.4762421
22. Irturk A, Benson B, Mirzaei S, Kastner R (2008) An FPGA design space exploration tool for matrix inversion architectures. In: Symposium on application specific processors, SASP 2008, pp 42-47. doi: 10.1109/SASP.2008. 4570784
23. Karkooti M, Cavallaro JR (2005) FPGA implementation of matrix inversion using QRD-RLS algorithm. In: Proc. 39th Asilomar conference on signals, systems, and computers
24. Kilpatrick D, Cameron-Jones R (1997) Numeric prediction using instance-based learning with encoding length selection. In: Progress in connectionist-based information systems, pp 984-987
25. Liaw C, Tsai CT, Ko CH (2012) Nonlinear quantization on hebbian-type associative memories. Appl Intell 36(4):824-833. doi: 10.1007/s10489-011-0299-7
26. Liu N, Wang H (2010) Ensemble based extreme learning machine. IEEE Signal Process Lett 17(8):754-757. doi: 10.1109/LSP.2010.2053356
27. Ma J, Dong ZY, Zang P (2006) Comparision of BR and QR eigenvalue algorithms for power system small signal stability analysis. IEEE Trans Power Syst 21(4):1848-1855 (Pubitemid 46357786)
28. Malathi V, Marimuthu N, Baskar S (2010) Intelligent approaches using support vector machine and extreme learning machine for transmission line protection. Neurocomputing 73(10-12):2160-2167
29. McLoone SF, Irwin GW (2001) Improving neural network training solutions using regularisation. Neurocomputing 37(1-4):71-90 (Pubitemid 32218908)
30. McLoone SF, Brown MD, Irwin GW, Lightbody G (1998) A hybrid linear/nonlinear training algorithm for feedforward neural networks. IEEE Trans Neural Netw 9(4):669-684 (Pubitemid 128750028)
31. Meyer C (2000) Matrix analysis and applied linear algebra. Society for Industrial and Applied Mathematics
32. Miche Y, Sorjamaa A, Bas P, Simula O, Jutten C, Lendasse A (2010) OP-ELM: optimally pruned extreme learning machine. IEEE Trans Neural Netw 21(1):158-162. doi: 10.1109/TNN.2009.2036259
33. Minhas R, Baradarani A, Seifzadeh S, Wu QJ (2010) Human action recognition using extreme learning machine based on visual vocabularies. Neurocomputing 73(10-12):1906-1917
34. Nizar A, Dong Z, Wang Y (2008) Power utility nontechnical loss analysis with extreme learning machine method. IEEE Trans Power Syst 23(3):946-955. doi: 10.1109/TPWRS.2008.926431
35. Noergaard T (2012) Embedded systems architecture: a comprehensive guide for engineers and programmers. Elsevier, Amsterdam
36. Pan Y, Ge SS, He H, Chen L (2009) Real-time face detection for human robot interaction. In: The 18th IEEE international symposium on robot and human interactive communication, RO-MAN 2009, pp 1016-1021. doi: 10.1109/ROMAN.2009. 5326349
37. Pao Y, Park G, Sobajic D (1994) Learning and generalization characteristics of the random vector functional-link net. Neurocomputing 6:163-168 (Pubitemid 24131868)
38. Quinlan JR (1993) Combining instance-based and model-based learning. Morgan Kaufmann, San Mateo, pp 236-243
39. Ramík D, Sabourin C, Moreno R, Madani K (2013) A machine learning based intelligent vision system for autonomous object detection and recognition. Appl Intell. doi: 10.1007/s10489-013-0461-5
40. Rao CR, Mitra SK (1972) Generalized inverse of matrices and its applications. Wiley, New York
41. Rong HJ, Huang GB, Ong YS (2008) Extreme learning machine for multi-categories classification applications. In: IEEE international joint conference on neural networks, IJCNN 2008. IEEE world congress on computational intelligence, pp 1709-1713. doi: 10.1109/IJCNN.2008.4634028
42. Rosado-Muñoz A, Soria-Olivas E, Gómez-Chova L, Vila-Francés J (2008) An IP core and GUI for implementing multilayer perceptron with a fuzzy activation function on configurable logic devices. J Univers Comput Sci 14(10):1678-1694
43. Saraswathi S, Sundaram S, Sundararajan N, Zimmermann M, Nilsen-Hamilton M (2011) ICGA-PSO-ELM approach for accurate multiclass cancer classification resulting in reduced gene sets in which genes encoding secreted proteins are highly represented. IEEE/ACM Trans Comput Biol Bioinform 8(2):452-463. doi: 10.1109/TCBB.2010.13
44. Sass R, Schmidt A (2010) Embedded systems design with platform FPGA: principles and practices. Elsevier, Amsterdam
45. Song Y, Lio P (2011) Epileptic EEG detection via a novel pattern recognition framework. In: 5th international conference on bioinformatics and biomedical engineering (iCBBE 2011), pp 1-6. doi: 10.1109/icbbe.2011.5780179
46. Sun ZL, Choi TM, Au KF, Yu Y (2008) Sales forecasting using extreme learning machine with applications in fashion retailing. Decis Support Syst 46(1):411-419. doi: 10.1016/j.dss.2008.07.009
47. Sun ZL, Ng KM, Soszynska-Budny J, Habibullah M (2011) Application of the LP-ELM model on transportation system lifetime optimization. IEEE Trans Intell Transp Syst 12(4):1484-1494. doi: 10.1109/TITS.2011.2160053
48. Szabó T, Horváth G (2004) An efficient hardware implementation of feed-forward neural networks. Appl Intell 21(2):143-158. doi: 10.1023/B:APIN.0000033634.62074.46
49. Talbi E (2009) Metaheuristics: from design to implementation. Wiley, New York
50. Tian H, Mao Z (2010) An ensemble ELM based on modified AdaBoost.RT algorithm for predicting the temperature of molten steel in ladle furnace. IEEE Trans Autom Sci Eng 7(1):73-80
51. Vani G, Savitha R, Sundararajan N (2010) Classification of abnormalities in digitized mammograms using extreme learning machine. In: 11th international conference on control automation robotics vision (ICARCV 2010), pp 2114-2117. doi: 10.1109/ICARCV.2010.5707794
52. Wang CW, You WH (2013) Boosting-svm: effective learning with reduced data dimension. Appl Intell 39(3):465-474. doi: 10.1007/s10489-013-0425-9
53. Wang G, Zhao Y, Wang D (2008) A protein secondary structure prediction framework based on the extreme learning machine. Neurocomputing 72(1-3):262-268
54. Wang L, Wan C (2008) Comments on "The extreme learning machine". IEEE Trans Neural Netw 19(8):1494-1495
55. Wang L, Yang B, Chen Y, Chen Z, Sun H (2013) Accelerating fcm neural network classifier using graphics processing units with cuda. Appl Intell. doi: 10.1007/s10489-013-0450-8
56. Xu Y, Dong Z, Meng K, Xu Z, Zhang R, Wu A, Wong K (2010) Earlier detection of risk of blackout by real-time dynamic security assessment based on extreme learning machines. In: International conference on power system technology (POWERCON 2010), pp 1-7. doi: 10.1109/POWERCON.2010.5666055
57. Yeu CW, Lim MH, Huang GB, Agarwal A, Ong YS (2006) A new machine learning paradigm for terrain reconstruction. IEEE Geosci Remote Sens Lett 3(3):382-386. doi: 10.1109/LGRS.2006.873687 (Pubitemid 44150329)
58. Youwen C, Tianyou C (2010) A model for steel billet temperature of prediction of heating furnace. In: 29th Chinese control conference (CCC), pp 1299-1302
59. Zhang D (2012) A new approach and system for attentive mobile learning based on seamless migration. Appl Intell 36(1):75-89. doi: 10.1007/s10489-010- 0245-0