Abstract
Many conventional artificial neural network (ANN) models are designed for one application domain only. The work presented in this paper describes ANN models that operate with a higher economy by sharing neurons across domains. The use of two different types of weights—static weights and dynamic weights—is a fundamental feature of the presented models. Results from a comprehensive series of experiments provide evidence for the meaningfulness of the proposed models.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Alnajjar, F., Yamashita, Y., Tani, J.: The hierarchical and functional connectivity of higher-order cognitive mechanisms: neurorobotic model to investigate the stability and flexibility of working memory. Frontiers in Neurorobotics (2013), doi:10.3389/fnbot.2013.00002
Augustine, G., Fitzpatrick, D., Purves, D.: Neuroscience, 3rd edn. Sinauer Associates Inc., U.S. (2004)
Bishop, C.: Neural Networks for Pattern Recognition. Oxford University Press (1996)
Blake, C., Merz, C.: Uci repository of machine learning databases, University of California, Irvine, Dept. of information and computer sciences (1998), http://www.ics.uci.edu/
Brighton, H., Selina, H.: Introducing Artificial Intelligence. Icon Books Ltd. (2003)
Maturana, H., Mcculloch, W., Pitts, W.: What the frog’s eye tells the frog’s brain. Proceedings of the Institute of Radio Engineers 47(11), 1940–1951 (1959)
Mehrotra, K., Monan, C., Ranka, S.: Elements of Artificial Neural Networks. The MIT Press (1997)
O’Shea, M.: Instant expert: The human brain. New Scientist 218(2911), 28 (2013); Instant Expert Series (8 pages)
Schuemann, A., Klawiter, A., Bonhoeffer, T., Wierenga, C.: Structural plasticity of gabaergic axons is regulated by network activity and gabaa receptor activation. Frontiers in Neural Circuits (2013), doi:10.3389/fncir.2013.00113
Schuster, A.: Application of artificial neural networks to multiple tasks. In: Proceedings of 2nd International Conference on Decision Support for Telecommunications and Information Society, DSTIS 2003, Warsaw, Poland (2003a)
Schuster, A.: A world according to artificial neural networks. Journal of Telecommunications and Information Technology 3, 102–107 (2003b)
Schuster, A.: Robustness in nature as a design principle for artificial intelligence. In: Schuster, A. (ed.) Robust Intelligent Systems, pp. 165–188. Springer (2008)
Spalding, K., Bergmann, O., Alkass, K., Bernard, S., Salehpour, M., Huttner, H., Boström, E., Westerlund, I., Vial, C., Buchholz, B., Possnert, G., Mash, D., Druid, H., Frisén, J.: Dynamics of hippocampal neurogenesis in adult humans. Cell 153(6), 1219–1227 (2013)
Wedeen, J., Rosene, D., Wang, R., Dai, G., Mortazavi, F., Hagmann, P., Kaas, J., Tseng, W.: The geometric structure of the brain fiber pathways. Science 335(6076), 1628–1634 (2012)
Werbos, P.: Beyond regression: new tools for prediction and analysis in the behavioral sciences. PhD Thesis, Harvard University, Cambridge, MA, USA (1974)
Yao, X.: Evolutionary artificial neural network. International Journal of Neural Systems 4(3), 203–220 (1993)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Schuster, A., Berrar, D. (2014). Towards Nature-Inspired Modularization of Artificial Neural Networks via Static and Dynamic Weights. In: Pham, T.D., Ichikawa, K., Oyama-Higa, M., Coomans, D., Jiang, X. (eds) Biomedical Informatics and Technology. ACBIT 2013. Communications in Computer and Information Science, vol 404. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-54121-6_19
Download citation
DOI: https://doi.org/10.1007/978-3-642-54121-6_19
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-54120-9
Online ISBN: 978-3-642-54121-6
eBook Packages: Computer ScienceComputer Science (R0)