Abstract
We present a model of a bidirectional three-layer neural network with sigmoidal units, which can be trained to learn arbitrary mappings. We introduce a bidirectional activation-based learning algorithm (BAL), inspired by O’Reilly’s supervised Generalized Recirculation (GeneRec) algorithm that has been designed as a biologically plausible alternative to standard error backpropagation. BAL shares several features with GeneRec, but differs from it by being completely bidirectional regarding the activation propagation and the weight updates. In pilot experiments, we test the learning properties of BAL using three artificial data sets with binary patterns of increasing complexity.
Access provided by Autonomous University of Puebla. Download to read the full chapter text
Chapter PDF
Similar content being viewed by others
Keywords
References
Almeida, L.: A learning rule for asynchronous perceptrons with feedback in a combinatorial environment. In: Proceedings of the IEEE First International Conference on Neural Networks, San Diego, CA (1987)
Hinton, G.E., McClelland, J.L.: Learning representations by recirculation. In: Neural Information Processing Systems, pp. 358–366. American Institute of Physics, New York (1988)
O’Reilly, R.: The Leabra model of neural interactions and learning in the neocortex. Ph.D. thesis, Carnegie Mellon University (1996)
O’Reilly, R.: Biologically plausible error-driven learning using local activation differences: The generalized recirculation algorithm. Neural Computation 8(5), 895–938 (1996)
O’Reilly, R., Munakata, Y., Frank, M., Hazy, T.: Computational Cognitive Neuroscience, 2nd edn. Wiki Book (2012)
Pineda, F.: Generalization of back-propagation to recurrent neural networks. Physics Review Letters 59, 2229–2232 (1987)
Rebrová, K., Pecháč, M., Farkaš, I.: Towards a robotic model of the mirror neuron system. In: The 3rd Joint IEEE International Conference on Development and Learning and on Epigenetic Robotics (2013)
Rumelhart, D., Hinton, G., Williams, R.: Learning internal representations by error propagation, vol. 1, pp. 318–362. MIT Press, Cambridge (1986)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Farkaš, I., Rebrová, K. (2013). Bidirectional Activation-based Neural Network Learning Algorithm. In: Mladenov, V., Koprinkova-Hristova, P., Palm, G., Villa, A.E.P., Appollini, B., Kasabov, N. (eds) Artificial Neural Networks and Machine Learning – ICANN 2013. ICANN 2013. Lecture Notes in Computer Science, vol 8131. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-40728-4_20
Download citation
DOI: https://doi.org/10.1007/978-3-642-40728-4_20
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-40727-7
Online ISBN: 978-3-642-40728-4
eBook Packages: Computer ScienceComputer Science (R0)