Skip to main content

Advertisement

Log in

A learning method of immune multi-agent neural networks

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

Abstract

Many different learning algorithms for neural networks have been developed, with advantages offered in terms of network structure, initial values of some parameters, learning speed, and learning accuracy. If we train the networks only on good examples, without noise and shortage, the neural network can be trained to classify, with reasonable accuracy, target patterns or random patterns, but not both. To solve this problem, we propose a learning method of immune multi-agent neural networks (IMANNs), which have agents of macrophages, B-cells and T-cells. Each agent employs a different type of neural network. Because the agents work cooperatively and competitively, IMANNs can automatically classify the training dataset into some subclasses. In this paper, two types of IMANNs are described and their classification capabilities are compared. In order to verify the effectiveness of our proposed method, we used two datasets: the dataset of the MONK’s problem (as a traditional classification problem) and a dataset from a medical diagnosis problem (hepatobiliary disorders).

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

Access this article

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.

Rent this article via DeepDyve

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14
Fig. 15
Fig. 16
Fig. 17
Fig. 18
Fig. 19
Fig. 20
Fig. 21
Fig. 22
Fig. 23
Fig. 24
Fig. 25
Fig. 26
Fig. 27
Fig. 28
Fig. 29

Similar content being viewed by others

Explore related subjects

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

References

  1. Robert AJ, Michael IJ, Steven JN, Geoffrey EH (1991) Adaptive mixtures of local experts. Neural Comput 3:79–87

    MATH  Google Scholar 

  2. Takumi I, Noboru M, Eiichiro T, Katsumi Y (1997) Extraction method of rules from reflective neural network architecture. In: Proceedings of the IEEE international conference on neural networks (ICNN’97), pp 510–515

  3. Shinichi O, Takumi I, Toshiyuki Y, Katsumi (2003) A proposal of immune multi-agents neural networks and its application to medical diagnostic system for hepatobiliary disorders. In: Proceedings of the 7th international conference on knowledge-based intelligent engineering systems (KES2003), vol 2, pp 526–532

  4. Takumi I, Shinichi O, Katsumi Y (2003) A classification method of medical database by immune multi-agent neural networks with planar lattice architecture. In: Proceedings of the 7th international conference on knowledge-based intelligent engineering systems (KES2003), vol 2, pp 380–387

  5. Naohiro F, Youji U, Ryouji S (1998) Learning of many-to-many relation between different kinds of sensory information using a neural network model for recognizing grasped objects. Brain Neural Netw 5(2):65–71

    Google Scholar 

  6. Takumi I, Shinichi O, Toshiyuki Y, Eiichiro T (1999) A learning method of neural network with lattice architecture, J Jpn Soc Fuzzy Theory 14(1):28–42

    Google Scholar 

  7. Takumi I, Ishida M, Terauchi M, Takahama T, Isomichi Y (2001) Extraction of emotion from facial expression by parallel sandglass type neural networks. In: Proceedings of the 5th international conference on knowledge-based intelligent engineering systems and allied technologies (KES2001), vol 2, pp 988–992

  8. Teuvo K (1995) Self-organizing maps. Information Sciences, vol 30. Springer, Berlin Heidelberg New York

  9. Shinichi O, Takumi I, Mutsuhiro T, Tetsuyuki T, Yoshinori I (2000) Adaptive evolutional learning method of neural networks using genetic algorithms in dynamic environment. In: Proceedings of the 4th international conference on knowledge-based intelligent engineering systems and allied technologies (KES2000), vol 2, pp 742–745

  10. Shinichi O, Takumi I, Mutsuhiro T, Tetsuyuki T, Yoshinori I (2002) A synthesis of structural adaptive learning algorithm in neural network based on the theory of evolution (in Japanese). Trans IPS Jpn 43(8):2728–2738

    Google Scholar 

  11. Sebastian BT et al (2001) The MONK’s problems—a performance comparison of different learning algorithms. Technical report CMU-CS-91-197, Carnegie Mellon University

  12. Takumi I, Shinichi O, Machi S, Kenneth JM, Katsumi Y (2004) Adaptive learning methods of reflective NN and immune multi-agent NN. In: Ichimura T, Yoshida K (eds) “Knowledge-Based Intelligent Systems for Health Care”. Advanced Knowledge International, pp 11–49

Download references

Acknowledgements

This research was performed with partial support of a Hiroshima City University Grant for Special Academic Research (General Studies).

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Takumi Ichimura.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Ichimura, T., Oeda, S., Suka, M. et al. A learning method of immune multi-agent neural networks. Neural Comput & Applic 14, 132–148 (2005). https://doi.org/10.1007/s00521-004-0448-6

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s00521-004-0448-6

Keywords

Navigation