Abstract
This work presents an MLP-like feed-forward network with two-dimensional layers partially connected and other features, such as configurable activation functions and batched backpropagation with different smoothing-momentum alternatives. We name this model eXtended Multi-Layer Perceptron (XMLP) because it extends the connectivity of the MLP. Here we describe its architecture, the various activation functions that it can use, its learning algorithm, and the possible use of discretization intended for hardware implementation. We also show a configurable graphic tool developed to train and simulate any MLP-like network (totally or partially connected). Finally, we present some results on speech recognition in order to compare total and partial connectivity, as well as continuous and discrete operation.
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
Caelli, T., Guan, L., Wen, W., Modularity in Neural Computing, Proceedings of the IEEE, Vol. 87, 9, 1497–1518 (1999)
Krause, A., and Hackbarth, H., Scaly Artificial Neural Networks for Speaker-Independent Recognition of Isolated Words, Proc. of the IEEE Int. Conf. On Acoustics, Speech and Signal Processing, ICASSP’ 89, 21–24 (1989)
Waibel, A., Hanazawa, T., Hinton, G., Shikano, K., Lang, K., Phoneme Recognition Using Time Delay Neural Networks, IEEE Transactions on Acoustics, Speech, and Signal Processing, Vol. 37, No. 3, 328–229 (1989)
Canas, A.; Ortega, J.; Fernández, F. J.; Prieto, A.; Pelayo, F. J., An approach to isolated word recognition using multilayer perceptrons, in: Prieto, A. (Ed.): Artificial Neural Networks. LNCS 540, 340–347, Springer-Verlag (1991)
Fernández-Rodríguez, J. J., Canas, A., Roca, E., Pelayo, F. J., Fernández-Mena, J., Prieto, A., Application of Artificial Neural Networks to Chest Image Classification, in: Mira, J., Cabestany, J., Prieto, A. (Eds.): New Trends in Neural Computation, LNCS 686, Springer Verlag (1993)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2003 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Canas, A., Ortigosa, E.M., Díaz, A.F., Ortega, J. (2003). XMLP: a Feed-Forward Neural Network with Two-Dimensional Layers and Partial Connectivity. In: Mira, J., Álvarez, J.R. (eds) Artificial Neural Nets Problem Solving Methods. IWANN 2003. Lecture Notes in Computer Science, vol 2687. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-44869-1_12
Download citation
DOI: https://doi.org/10.1007/3-540-44869-1_12
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-40211-4
Online ISBN: 978-3-540-44869-3
eBook Packages: Springer Book Archive