Avoiding Catastrophic Forgetting by a Biologically Inspired Dual-Network Memory Model

  • Motonobu Hattori
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7664)


In neural networks, when new patterns are learned by a network, they radically interfere with previously stored patterns. This drawback is called catastrophic forgetting. In this paper, we propose a biologically inspired dual-network memory model which can much reduce this forgetting. The proposed model consists of two distinct neural networks: a hippocampal network and a neocortical network. Information given is first stored in a hippocampal network and then it is transferred to the neocortical network. The chaotic recall of the hippocampal network enables the extraction of original patterns, and owing to this, they can be interleaved with previous information stored in the neocortical network. Thus, catastrophic forgetting can be avoided. Computer simulation results show the effectiveness of the proposed dual-network memory model.


Catastrophic forgetting chaotic neural network complementary learning systems dual-network hippocampus neuronal turnover 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    French, R.M.: Pseudo-recurrent connectionist networks: An approach to the “sensitivity-stability” dilemma. Connection Science 9(4), 353–379 (1997)CrossRefGoogle Scholar
  2. 2.
    Ans, B., Rousset, S.: Avoiding catastrophic forgetting by coupling two reverberating neural networks. Academie des Sciences, Sciences de la vie 320, 989–997 (1997)Google Scholar
  3. 3.
    McClelland, J.L., McNaughton, B.L., O’Reilly, R.C.: Why there are complementary learning systems in the hippocampus and neocortex: Insights from the successes and failures of connectionist models of learning and memory. Psychological Review 102(3), 419–457 (1995)CrossRefGoogle Scholar
  4. 4.
    Aihara, K., Takabe, T., Toyoda, M.: Chaotic Neural Networks. Physics Letters A 144(6-7), 333–340 (1990)MathSciNetCrossRefGoogle Scholar
  5. 5.
    Wakagi, Y., Hattori, M.: A Model of Hippocampal Learning with Neuronal Turnover in Dentate Gyrus. International Journal of Mathematics and Computers in Simulation 2(2), 215–222 (2008)Google Scholar
  6. 6.
    Hattori, M.: Dual-Network Memory Model Using a Chaotic Neural Network. In: Proceedings of IEEE and INNS International Joint Conference on Neural Networks, Barcelona, July 18-23, pp. 1678–1682 (2010)Google Scholar
  7. 7.
    Hattori, M.: Extraction of Patterns from a Hippocampal Network Using Chaotic Recall. In: Gaol, F.L., Strouhal, J. (eds.) Recent Researches in Computational Intelligence and Information Security, pp. 27–32. WSEAS Press (2011)Google Scholar
  8. 8.
    Norman, K.A., O’Reilly, R.C.: Modeling Hippocampal and Neocortical Contribution to Recognition Memory: A Complementary-Learning-Systems Approach. Psychological Review 110(4), 611–646 (2003)CrossRefGoogle Scholar
  9. 9.
    Yeckel, M.F., Berger, T.W.: Feedforward excitation of the hippocampus the trisynaptic pathway. Proceedings of the National Academy of Sciences of the USA 87, 5832–5836 (1990)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Motonobu Hattori
    • 1
  1. 1.Interdisciplinary Graduate School of Medicine and EngineeringUniversity of YamanashiKofuJapan

Personalised recommendations