Skip to main content
SpringerLink
Log in

Weights optimization for multi-instance multi-label RBF neural networks using steepest descent method

  • Original Article
  • Published:
Neural Computing and Applications Aims and scope Submit manuscript

Abstract

Multi-instance multi-label learning (MIML) is an innovative learning framework where each sample is represented by multiple instances and associated with multiple class labels. In several learning situations, the multi-instance multi-label RBF neural networks (MIMLRBF) can exploit connections between the instances and the labels of an MIML example directly, while most of other algorithms cannot learn that directly. However, the singular value decomposition (SVD) method used to compute the weights of the output layer will cause augmented overall error in network performance when training data are noisy or not easily discernible. This paper presents an improved approach to learning algorithms used for training MIMLRBF. The steepest descent (SD) method is used to optimize the weights after they are initialized by the SVD method. Comparing results employing diverse learning strategies shows interesting outcomes as have come out of this paper.

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

Access this article

Log in via an institution

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

Similar content being viewed by others

Notes

  1. A Founder server with 4G RAM and Intel Xeon E5504 CPU is used to conduct the experiments.

References

  1. Zhou Z-H, Zhang M-L (2007) Multi-instance multi-label learning with application to scene classification. In: B Schǒlkopf, J Platt, T Hoffman (eds) Adv Neural Inf Process Syst 19: 1609–1616

  2. Zhang M-L, Wang Z-J (2009) MIMLRBF: RBF neural networks for multi-instance multi-label learning. Neurocomputing 72:3951–3956

    Article  Google Scholar 

  3. Chen W, Jiao L (2010) Adaptive tracking for periodically time-varying and nonlinearly parameterized systems using multilayer neural networks. IEEE Trans Neural Netw 21(2):345–351

    Article  Google Scholar 

  4. Chen W, Jiao LC, Wu J (2011) Decentralized backstepping output-feedback control for stochastic interconnected systems with time-varying delays using neural networks. Neural Comput Appl. doi:10.1007/s00521-011-0590-x

    Google Scholar 

  5. Zhao Z, Shan X (2007) Optimization approach based on genetic algorithm for RBF neural network (in Chinese). Comput Eng 33(6):211–212

    Google Scholar 

  6. Bishop CM (1995) Neural networks for pattern recognition. Oxford University Press, New York

    Google Scholar 

  7. Dietterich TG, Lathrop RH, Lozano-Pérez T (1997) Solving the multiple-instance problem with axis-parallel rectangles. Artif Intell 89(1–2):31–71

    Article  MATH  Google Scholar 

  8. Schapire RE, Singer Y (2000) BoosTexter: a boosting-based system for text categorization. Mach Learn 39(2–3):135–168

    Article  MATH  Google Scholar 

  9. Boutell MR, Luo J, Shen X, Brown CM (2004) Learning multi-label scene classification. Pattern Recogn 37(9):1757–1771

    Article  Google Scholar 

  10. Zafra A, Romero C, Ventura S (2011) Multiple instance learning for classifying students in learning management systems. Expert Syst Appl 38:15020–15031

    Article  Google Scholar 

  11. ZhouZ-H, Zhang M-L, Huang S-J, Y-F Li (2008) MIML: a framework for learning with ambiguous objects, CORR abs/0808.3231

  12. Gǎrtner T, Flach PA, Smola AJ (2002) Multi-instance kernels. In: Proceedings of the 19th international conference on machine learning, Sydney, pp 179–186

  13. Smola AJ, Vishwanathan SVN, T. Hofmann (2005) Kernel methods for missing variables. In: Proceedings of the 10th international workshop on artificial intelligence and statistics, Barbados, pp 325–332

  14. Kelley JE (1960) The cutting-plane method for solving convex programs. J Soc Ind Appl Math 8(4):703–712

    Article  MathSciNet  Google Scholar 

  15. Edgar GA (1995) Measure, topology, and fractal geometry. 3rd print, Springer, Berlin

  16. Zhang M-L, Zhou Z-H (2009) Multi-instance clustering with applications to multi-instance prediction. Appl Intell 31(1):47–68

    Article  Google Scholar 

  17. Montazer GA, Sabzevari Reza, Ghorbani Fatemeh (2009) Three-phase strategy for the OSD learning method in RBF neural networks. Neurocomputing 72:1797–1802

    Article  Google Scholar 

  18. Cohen S, Intrator N (1996) Global optimization of RBF networks. IEEE Trans Neural Netw 7(4):969–984

    Google Scholar 

  19. Maron O, Ratan AL (1998) Multiple-instance learning for natural scene classification. In: Proceedings of the 15th international conference on machine learning, WI, pp 341–349

  20. Zhang M-L, Zhou Z-H (2008) M3MIML: a maximum margin method for multi-instance multi-label learning. In: Proceedings of the 8th IEEE international conference on data mining (ICDM’08), Pisa, pp 688–697

  21. Sebastiani F (2002) Machine learning in automated text categorization. ACM Comput Surv 34(1):1–47

    Article  Google Scholar 

  22. Andrews S, Tsochantaridis I, Hofmann T (2003) Support vector machines for multiple-instance learning. Adv Neural Inf Process Syst 15, MIT Press, Cambridge, pp 561–568

Download references

Acknowledgments

This work is supported by the Fundamental Research Funds for the Central Universities (No. 09CX04031A). The authors are grateful for the anonymous reviewers who made constructive comments.

Author information

Authors and Affiliations

  1. College of Computer and Communication Engineering, China University of Petroleum, Qingdao, 266555, China

    Cunhe Li & Guoqiang Shi

Authors
  1. Cunhe Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Guoqiang Shi
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Cunhe Li.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Li, C., Shi, G. Weights optimization for multi-instance multi-label RBF neural networks using steepest descent method. Neural Comput & Applic 22, 1563–1569 (2013). https://doi.org/10.1007/s00521-012-0815-7

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00521-012-0815-7

Keywords

Search

Navigation