Nothing Special   »   [go: up one dir, main page]
Skip to main content
Springer Nature Link
Log in

A review of online learning in supervised neural networks

  • Invited Review
  • Published:
Neural Computing and Applications Aims and scope Submit manuscript

Abstract

Learning in neural networks can broadly be divided into two categories, viz., off-line (or batch) learning and online (or incremental) learning. In this paper, a review of a variety of supervised neural networks with online learning capabilities is presented. Specifically, we focus on articles published in main indexed journals in the past 10 years (2003–2013). We examine a number of key neural network architectures, which include feedforward neural networks, recurrent neural networks, fuzzy neural networks, and other related networks. How the online learning methodologies are incorporated into these networks is exemplified, and how they are applied to solving problems in different domains is highlighted. A summary of the review that covers different network architectures and their applications is presented.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10

Similar content being viewed by others

Explore related subjects

Discover the latest articles, news and stories from top researchers in related subjects.

References

  1. Gupta M, Jin L, Homma N (2003) Static and dynamic neural networks: from fundamentals to advanced theory, vol 1. Wiley-IEEE Press, Hoboken, pp 507–577

    Book  Google Scholar 

  2. Kartalopoulos S (1996) Understanding neural networks and fuzzy logic: basic concepts and applications. Wiley-IEEE Press, Hoboken, pp 61–119

    MATH  Google Scholar 

  3. Definition of a Neural Network (2013) Neural networks module. http://uhavax.hartford.edu/compsci/neural-networks-definition.html. Accessed 1 Aug 2013

  4. Hudson D, Cohen M (2000) Neural networks and artificial intelligence for biomedical engineering, vol 1. Wiley-IEEE Press, Hoboken, pp 13–28

    Google Scholar 

  5. Saad D (2009) On-line learning in neural networks. Cambridge University Press, Cambridge, p 17

  6. Lim CP, Harrison RF (1997) An incremental adaptive network for on-line supervised learning and probability estimation. Neural Netw 10(5):925–939

    Article  Google Scholar 

  7. Choy MC, Srinivasan D, Cheu RL (2006) Neural networks for continuous online learning and control. IEEE Trans Neural Networks 17(6):1511–1531

    Article  Google Scholar 

  8. Suresh S, Sundararajan N, Savitha R (2013) Supervised learning with complex-valued neural networks. Stud Comput Intell 421:31–71

    Article  Google Scholar 

  9. Wan S, Banta LE (2006) Parameter incremental learning algorithm for neural networks. IEEE Trans Neural Networks 17(6):1424–1438

    Article  Google Scholar 

  10. Sanz J, Perera R, Huerta C (2012) Gear dynamics monitoring using discrete wavelet transformation and multi-layer perceptron neural networks. Appl Soft Comput 12(9):2867–2878

    Article  Google Scholar 

  11. González A, Dorronsoro JR (2008) Natural conjugate gradient training of multilayer perceptrons. Neurocomputing 71(13–15):2499–2506

    Article  Google Scholar 

  12. Campolucci P, Uncini A, Piazza F, Rao BD (1999) On-line learning algorithms for locally recurrent neural networks. IEEE Trans Neural Networks 10(2):253–271

    Article  Google Scholar 

  13. Jung S, Kim SS (2008) Control experiment of a wheel-driven mobile inverted pendulum using neural network. IEEE Trans Control Syst Technol 16(2):297–303

    Article  Google Scholar 

  14. Zhou S, Lai KK (2011) An improved EMD online learning-based model for gold market forecasting. Intell Decis Technol 10:75–84

    Article  Google Scholar 

  15. Zhou S, Lai KK, Yen J (2012) A dynamic meta-learning rate-based model for gold market forecasting. Expert Syst Appl 39(6):6168–6173

    Article  Google Scholar 

  16. Radial basis function network (2013) Wikipedia. http://en.wikipedia.org/wiki/Radial_basis_function_network. Accessed 1 Aug 2013

  17. Loreto G, Garrido R (2006) Stable neurovisual servoing for robot manipulators. IEEE Trans Neural Networks 17(4):953–965

    Article  Google Scholar 

  18. Yu H, Xie T, Paszczyñski S, Wilamowski BM (2011) Advantages of radial basis function networks for dynamic system design. IEEE Trans Ind Electron 58(12):5438–5450

    Article  Google Scholar 

  19. Ho KJ, Leung CS, Sum J (2010) Convergence and objective functions of some fault/noise-injection-based online learning algorithms for RBF networks. IEEE Trans Neural Networks 21(6):938–947

    Article  Google Scholar 

  20. Suresh S, Sundararajan N (2012) An on-line learning neural controller for helicopters performing highly nonlinear maneuvers. Appl Soft Comput 12(1):360–371

    Article  Google Scholar 

  21. Li Y, Sundararajan N, Saratchandran P, Wang Z (2004) Robust neuro-H∞ controller design for aircraft auto-landing. IEEE Trans Aerosp Electron Syst 40(1):158–167

    Article  Google Scholar 

  22. Lee KM, Street WN (2003) An adaptive resource-allocating network for automated detection, segmentation, and classification of breast cancer nuclei topic area: image processing and recognition. IEEE Trans Neural Networks 14(3):680–687

    Article  Google Scholar 

  23. Corradini ML, Fossi V, Giantomassi A, Ippoliti G, Longhi S, Orlando G (2012) Minimal resource allocating networks for discrete time sliding mode control of robotic manipulators. IEEE Trans Ind Inf 8(4):733–745

    Article  Google Scholar 

  24. Nanda SK, Tripathy DP (2011) Application of functional link artificial neural network for prediction of machinery noise in opencast mines. Adv Fuzzy Syst. doi:10.1155/2011/831261

    Google Scholar 

  25. Pao YH, Takefuji Y (1992) Functional-link net computing: theory, system architecture, and functionalities. Computer 25(5):76–79

    Article  Google Scholar 

  26. Wu CF, Lin CJ, Lee CY (2011) A functional neural fuzzy network for classification applications. Expert Syst Appl 38(5):6202–6208

    Article  Google Scholar 

  27. Chen CH, Lin CJ, Lin CT (2008) A functional-link-based neurofuzzy network for nonlinear system control. IEEE Trans Fuzzy Syst 16(5):1362–1378

    Article  Google Scholar 

  28. Mehdi A (2013) Currency exchange rate prediction using wavelet network. Basrah J Sci 31(2):44–53

    Google Scholar 

  29. Akay M (1998) Time frequency and wavelets in biomedical signal processing. Wiley-IEEE Press, Hoboken, pp 669–684

    MATH  Google Scholar 

  30. El-Sousy FFM (2010) Hybrid based wavelet-neural-network tracking control for permanent-magnet synchronous motor servo drives. IEEE Trans Ind Electron 57(9):3157–3166

    Article  Google Scholar 

  31. Lin FJ, Shieh HJ, Huang PK (2006) Adaptive wavelet neural network control with hysteresis estimation for piezo-positioning mechanism. IEEE Trans Neural Networks 17(2):432–444

    Article  Google Scholar 

  32. El-Sousy FFM (2011) Robust wavelet-neural-network sliding-mode control system for permanent magnet synchronous motor drive. IET Electr Power Appl 5(1):113–132

    Article  Google Scholar 

  33. Lin CJ, Chin CC (2004) Prediction and identification using wavelet-based recurrent fuzzy neural networks. IEEE Trans Syst Man Cybern B Cybern 34(5):2144–2154

    Article  Google Scholar 

  34. Lin CM, Li HY (2012) A novel adaptive wavelet fuzzy cerebellar model articulation control system design for voice coil motors. IEEE Trans Ind Electron 59(4):2024–2033

    Article  Google Scholar 

  35. Recurrent neural network (2013) Wikipedia. http://en.wikipedia.org/wiki/Recurrent_neural_network. Accessed 1 Aug 2013

  36. Graves A (2012) Supervised sequence labelling with recurrent neural networks. Stud Comput Intell 385:15–35

    Article  Google Scholar 

  37. Liu Z, Elhanany I (2008) A fast and scalable recurrent neural network based on stochastic meta descent. IEEE Trans Neural Networks 19(9):1652–1658

    Article  Google Scholar 

  38. Shibata T, Tabata H, Schaal S, Kawato M (2005) A model of smooth pursuit in primates based on learning the target dynamics. Neural Networks 18(3):213–224

    Article  MATH  Google Scholar 

  39. Banaei MR, Kami A (2011) Interline power flow controller (IPFC) based damping recurrent neural network controllers for enhancing stability. Energy Convers Manag 52(7):2629–2636

    Article  Google Scholar 

  40. Lin CT, Chang CL, Cheng WC (2004) A recurrent fuzzy cellular neural network system with automatic structure and template learning. IEEE Trans Circuits and Systems I: Regular Papers 51(5):1024–1035

    Google Scholar 

  41. Ajoudani A, Erfanian A (2009) A neuro-sliding-mode control with adaptive modeling of uncertainty for control of movement in paralyzed limbs using functional electrical stimulation. IEEE Trans Biomed Eng 56(7):1771–1780

    Article  Google Scholar 

  42. Lin FJ, Teng LT, Chu H (2008) A robust recurrent wavelet neural network controller with improved particle swarm optimization for linear synchronous motor drive. IEEE Trans Power Electron 23(6):3067–3078

    Article  Google Scholar 

  43. Lin FJ, Teng LT, Lin JW, Chen SY (2009) Recurrent functional-link-based fuzzy-neural-network-controlled induction-generator system using improved particle swarm optimization. IEEE Trans Ind Electron 56(5):1557–1577

    Article  Google Scholar 

  44. Teng LT, Lin FJ, Chiang HC, Lin JW (2009) Recurrent wavelet neural network controller with improved particle swarm optimisation for induction generator system. IET Electr Power Appl 3(2):147–159

    Article  Google Scholar 

  45. Hénaff P, Scesa V, Ouezdou FB, Bruneau O (2011) Real time implementation of CTRNN and BPTT algorithm to learn on-line biped robot balance: experiments on the standing posture. Control Eng Pract 19(1):89–99

    Article  Google Scholar 

  46. Lin YY, Chang JY, Lin CT (2013) Identification and prediction of dynamic systems using an interactively recurrent self-evolving fuzzy neural network. IEEE Trans Neural Netw Learn Syst 24(2):310–321

    Article  Google Scholar 

  47. Juang CF, Chen JS (2007) A recurrent fuzzy-network-based inverse modeling method for a temperature system control. IEEE Trans Syst Man Cybern C Appl Rev 37(3):410–417

    Article  Google Scholar 

  48. Mirikitani DT, Nikolaev N (2010) Efficient online recurrent connectionist learning with the ensemble Kalman filter. Neurocomputing 73(4–6):1024–1030

    Article  Google Scholar 

  49. Elman JL (1990) Finding structure in time. Cogn Sci 14:179–211

    Article  Google Scholar 

  50. Hammer B (1997) Generalization of Elman networks. Lect Notes Comput Sci 1327:409–414

    Article  Google Scholar 

  51. Lin FJ, Hung YC, Chen SY (2009) FPGA-based computed force control system using Elman neural network for linear ultrasonic motor. IEEE Trans Ind Electron 56(4):1238–1253

    Article  Google Scholar 

  52. Lin FJ, Hung YC (2009) FPGA-based Elman neural network control system for linear ultrasonic motor. IEEE Trans Ultrason Ferroelectr Freq Control 56(1):101–113

    Article  Google Scholar 

  53. Wen S, Zheng W, Zhu J, Li X, Chen S (2012) Elman fuzzy adaptive control for obstacle avoidance of mobile robots using hybrid force/position incorporation. IEEE Trans Syst Man Cybern C Appl Rev 42(4):603–608

    Article  Google Scholar 

  54. Mbede JB, Huang X, Wang M (2003) Robust neuro-fuzzy sensor-based motion control among dynamic obstacles for robot manipulators. IEEE Trans Fuzzy Syst 11(2):249–261

    Article  Google Scholar 

  55. Carpenter GA, Grossberg S (1987) A massively parallel architecture for a self-organizing neural pattern recognition machine. Comput Vis Graph Image Process 37:54–115

    Article  MATH  Google Scholar 

  56. Carpenter GA, Grossberg S, Reynolds JH (1991) ARTMAP: supervised real-time learning and classification of nonstationary data by a self-organizing neural network. Neural Netw 4:565–588

    Article  Google Scholar 

  57. Carpenter GA, Grossberg S, Markuzon N, Reynolds JH, Rosen DB (1992) Fuzzy ARTMAP: a neural network architecture for incremental supervised learning of analog multidimensional maps. IEEE Trans Neural Netw 3(5):698–713

    Article  Google Scholar 

  58. Carpenter GA, Martens S, Ogas OJ (2005) Self-organizing information fusion and hierarchical knowledge discovery: a new framework using ARTMAP neural networks. Neural Netw 18:287–295

    Article  Google Scholar 

  59. Carpenter GA, Gaddam SC (2010) Biased ART: a neural architecture that shifts attention toward previously disregarded features following an incorrect prediction. Neural Netw 23:435–451

    Article  Google Scholar 

  60. Lim CP, Harrison RF (2003) Online pattern classification with multiple neural network systems: an experimental study. IEEE Trans Syst Man Cybern C Appl Rev 33(2):235–247

    Google Scholar 

  61. Yap KS, Lim CP, Au MT (2011) Improved GART neural network model for pattern classification and rule extraction with application to power systems. IEEE Trans Neural Net 22(12):2310–2323

    Article  Google Scholar 

  62. Yap KS, Lim CP, Abidin IZ (2008) A hybrid ART-GRNN online learning neural network with insensitive loss function. IEEE Trans Neural Netw 19(9):1641–1646

    Article  Google Scholar 

  63. Lee EWM, Lim CP, Yuen RKK, Lo SM (2004) A hybrid neural network model for noisy data regression. IEEE Trans Syst Man Cybern B Cybern 34(2):951–960

    Article  Google Scholar 

  64. Akhbardeh A, Junnila S, Koivistoinen T, Varri A (2007) An intelligent ballistocardiographic chair using a novel SF-ART neural network and biorthogonal wavelets. J Med Syst 31:69–77

    Article  Google Scholar 

  65. Anton-Rodriguez M, Diaz-Pernas FJ, Diez-Higuera JF, Martinez-Zarzuela M, Gonzalez-Ortega D, Boto-Giralda D (2009) Recognition of coloured and textured images through a multi-scale neural architecture with orientational filtering and chromatic diffusion. Neurocomputing 72:3713–3725

    Article  Google Scholar 

  66. Cai Y, Wang JZ, Tang Y, Yang YC (2011) An efficient approach for electric load forecasting using distributed ART (adaptive resonance theory) & HS-ARTMAP (hyper-spherical ARTMAP network) neural network. Energy 36:1340–1350

    Article  Google Scholar 

  67. Lim CP, Leong JH, Kuan MM (2005) A hybrid neural network system for pattern classification tasks with missing features. IEEE Trans Pattern Anal Mach Intell 27(4):648–653

    Article  Google Scholar 

  68. Simpson PK (1992) Fuzzy min–max neural networks-part 1: classification. IEEE Trans Neural Netw 3(5):776–786

    Article  Google Scholar 

  69. Nandedkar AV, Biswas PK (2009) A granular reflex fuzzy min–max neural network for classification. IEEE Trans Neural Netw 20(7):1117–1134

    Article  Google Scholar 

  70. Zhang H, Liu J, Ma D, Wang Z (2011) Data-core-based fuzzy min–max neural network for pattern classification. IEEE Trans Neural Netw 22(12):2339–2352

    Article  Google Scholar 

  71. Quteishat A, Lim CP, Tan KS (2010) A modified fuzzy min-max neural network with a genetic-algorithm-based rule extractor for pattern classification. IEEE Trans Syst Man Cybern A Syst Hum 40(3):641–650

    Article  Google Scholar 

  72. Fuzzy neural network (2013) Scholarpedia. http://www.scholarpedia.org/article/Fuzzy_neural_network. Accessed 1 Aug 2013

  73. Lin FJ, Huang MS, Yeh PY, Tsai HC, Kuan CH (2012) DSP-based probabilistic fuzzy neural network control for li-ion battery charger. IEEE Trans Power Electron 27(8):3782–3794

    Article  Google Scholar 

  74. Gao Y, Er MJ (2005) An intelligent adaptive control scheme for postsurgical blood pressure regulation. IEEE Trans Neural Netw 16(2):475–483

    Article  MathSciNet  Google Scholar 

  75. Srinivasan D, Choy MC, Cheu RL (2006) Neural networks for real-time traffic signal control. IEEE Trans Intell Transp Syst 7(3):261–272

    Article  Google Scholar 

  76. Choy MC, Srinivasan D, Cheu RL (2003) Cooperative, hybrid agent architecture for real-time traffic signal control. IEEE Trans Syst Man Cybern A Syst Hum 33(5):597–607

    Article  Google Scholar 

  77. Wai RJ, Lee JD (2009) Robust levitation control for linear maglev rail system using fuzzy neural network. IEEE Trans Control Syst Technol 17(1):4–14

    Article  Google Scholar 

  78. Wai RJ, Lee JD (2008) Adaptive fuzzy-neural-network control for maglev transportation system. IEEE Trans Neural Netw 19(1):54–70

    Article  MathSciNet  Google Scholar 

  79. Juang CF, Tsao YW (2008) A self-evolving interval type-2 fuzzy neural network with online structure and parameter learning. IEEE Trans Fuzzy Syst 16(6):1411–1424

    Article  Google Scholar 

  80. Wang N, Er MJ, Meng X (2009) A fast and accurate online self-organizing scheme for parsimonious fuzzy neural networks. Neurocomputing 72(16–18):3818–3829

    Article  Google Scholar 

  81. Wang N, Er MJ, Meng X (2009) An online self-constructing fuzzy neural network with restrictive growth. In: Yu W (ed) Recent advances in intelligent control systems. Springer, London, pp 225–247

    Chapter  Google Scholar 

  82. Rubaai A, Young P (2011) EKF-based PI-/PD-like fuzzy-neural-network controller for brushless drives. IEEE Trans Ind Appl 47(6):2391–2401

    Article  Google Scholar 

  83. Zhai J, Zhou J, Zhang L, Hong W (2010) Behavioral modeling of power amplifiers with dynamic fuzzy neural networks. IEEE Microwave Wirel Compon Lett 20(9):528–530

    Article  Google Scholar 

  84. Wai RJ, Yang ZW (2008) Adaptive fuzzy neural network control design via a T–S fuzzy model for a robot manipulator including actuator dynamics. IEEE Trans Syst Man Cybern B Cybern 38(5):1326–1346

    Article  Google Scholar 

  85. Lin FJ, Hung YC, Hwang JC, Tsai MT (2013) Fault tolerant control of six-phase motor drive system using Takagi–Sugeno–Kang type fuzzy neural network with asymmetric membership function. IEEE Trans Power Electron 28(7):3557–3572

    Article  Google Scholar 

  86. Lin FJ, Chou PH, Kung YS (2008) Robust fuzzy neural network controller with nonlinear disturbance observer for two-axis motion control system. IET Control Theory Appl 2(2):151–167

    Article  Google Scholar 

  87. Wai RJ, Shih LC (2012) Adaptive fuzzy-neural-network design for voltage tracking control of a DC–DC boost converter. IEEE Trans Power Electron 27(4):2104–2115

    Article  Google Scholar 

  88. Kong X, Hu C, Han C (2010) A self-stabilizing MSA algorithm in high-dimension data stream. Neural Netw 23:865–871

    Article  Google Scholar 

  89. Peng YF, Wai RJ, Lin CM (2004) Implementation of LLCC-resonant driving circuit and adaptive CMAC neural network control for linear piezoelectric ceramic motor. IEEE Trans Ind Electron 51(1):35–48

    Article  Google Scholar 

  90. Kohata Y, Yamauchi K, Kurihara M (2009) Quick maximum power point tracking of photovoltaic using online learning neural network. Neural Inf Process 5863:606–613

    Google Scholar 

  91. Leite D, Costa P, Gomide F (2013) Evolving granular neural networks from fuzzy data streams. Neural Netw 38:1–16

    Article  Google Scholar 

  92. Rajapakse A, Furuta K, Kondo S (2002) Evolutionary learning of fuzzy logic controllers and their adaptation through perpetual evolution. IEEE Trans Fuzzy Syst 10(3):309–321

    Article  Google Scholar 

  93. Van Lint JWC (2008) Online learning solutions for freeway travel time prediction. Intell Transp Syst IEEE Trans 9(1):38–47

    Article  Google Scholar 

  94. Yu DL, Chang TK, Yu DW (2005) Fault tolerant control of multivariable processes using auto-tuning PID controller. IEEE Trans Syst Man Cybern B Cyber 35(1):32–43

    Article  Google Scholar 

  95. Shih F (2010) Image processing and pattern recognition: fundamentals and techniques. Wiley-IEEE Press, Hoboken, pp 306–352

    Book  Google Scholar 

  96. Guo P, Jiang Z, Lin S, Yao Y (2012) Combining LVQ with SVM technique for image semantic annotation. Neural Comput Appl 21:735–746

    Article  Google Scholar 

  97. Lin KP, Chen MS (2011) On the design and analysis of the privacy-preserving SVM classifier. IEEE Trans Knowl Data Eng 23(11):1704–1717

    Article  Google Scholar 

  98. Zheng J, Yu H, Shen F, Zhao J (2013) An online incremental learning support vector machine for large-scale data. Neural Comput Appl 22(5):1023–1035

    Article  Google Scholar 

  99. Wang HQ, Cai YN, Sun FC (2011) A non-biased form of least squares support vector classifier and its fast online learning. Neural Comput Appl 20(7):1075–1085

    Article  Google Scholar 

  100. Kawano S, Okumura D, Tamura H, Tanaka H, Tanno K (2009) Online learning method using support vector machine for surface-electromyogram recognition. Artif Life Robot 13(2):483–487

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. University of South Australia, Adelaide, Australia

    Lakhmi C. Jain

  2. University of Malaya, Kuala Lumpur, Malaysia

    Manjeevan Seera

  3. Deakin University, Geelong, VIC, Australia

    Chee Peng Lim

  4. Gandhigram Rural Institute-Deemed University, Gandhigram, Tamil Nadu, India

    P. Balasubramaniam

Authors
  1. Lakhmi C. Jain
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Manjeevan Seera
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Chee Peng Lim
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. P. Balasubramaniam
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Lakhmi C. Jain.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Jain, L.C., Seera, M., Lim, C.P. et al. A review of online learning in supervised neural networks. Neural Comput & Applic 25, 491–509 (2014). https://doi.org/10.1007/s00521-013-1534-4

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00521-013-1534-4

Keywords

Search

Navigation