Abstract
Many Artificial Neural Networks design algorithms or learning methods imply the minimization of an error objective function. During learning, weight values are updated following a strategy that tends to minimize the final mean error in the Network performance. Weight values are classically seen as a representation of the synaptic weights in biological neurons and their ability to change its value could be interpreted as artificial plasticity inspired by this biological property of neurons. In such a way, metaplasticity is interpreted in this paper as the ability to change the efficiency of artificial plasticity giving more relevance to weight updating of less frequent activations and resting relevance to frequent ones. Modeling this interpretation in the training phase, the hypothesis of an improved training is tested in the Multilayer Perceptron with Backpropagation case. The results show a much more efficient training maintaining the Artificial Neural Network performance.
This research has been supported by the National Spanish Research Institution ”Comisíon Interministerial de Ciencia y Tecnología - CICYT” as part of the project AGL2006-12689/AGR.
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
Andina, D., Pham, D.T. (eds.): Computational Intelligence for Engineering and Manufacturing. Springer, Heidelberg (March 2007)
Godoy Simoes, M., Ropero Pelaez, J.: A computational model of synaptic metaplasticity. In: Proceedings of the International Joint Conference on Neural Networks (1999)
Friedrich, P., Tompa, P.: Synaptic metaplasticity and the local charge effect in postsynaptic densities. Trends in Neuroscience 3(21), 97–101 (1998)
Andina, D., Jevtić, A.: Improved multilayer perceptron design by weighted learning. In: Proc. of the 2007 IEEE International Symposium on Industrial Electronics, ISIE 2007, Vigo, Spain, vol. 15 (2007)
Alarcón, M.J., Torres-Alegre, S., Andina, D.: Behavior of a binary detector based on an ann digital implementation in the presence of seu simulations. In: Proc. of III World Multiconference on Systemics, Cybernetics and Informatics (SCI’99) and 5th International Conference on Information Systems Analysis and Synthesis (ISAS’99), Orlando, Florida, USA, July-August 1999, vol. 3, pp. 616–619 (1999)
Marcum, J.: A statistical theory of target detection by pulsed radar. IEEE Transactions on Information Theory 6(2), 59–267 (1960)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2007 Springer Berlin Heidelberg
About this paper
Cite this paper
Andina, D., Jevtić, A., Marcano, A., Barrón Adame, J.M. (2007). Error Weighting in Artificial Neural Networks Learning Interpreted as a Metaplasticity Model. In: Mira, J., Álvarez, J.R. (eds) Bio-inspired Modeling of Cognitive Tasks. IWINAC 2007. Lecture Notes in Computer Science, vol 4527. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-73053-8_24
Download citation
DOI: https://doi.org/10.1007/978-3-540-73053-8_24
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-73052-1
Online ISBN: 978-3-540-73053-8
eBook Packages: Computer ScienceComputer Science (R0)