Abstract
This paper proposes a novel recognition model, a recurrent fuzzy associative memory(RFAM), for recognizing time-series patterns contained ambiguity. RFAM is basically extended from FAM(Fuzzy Associative memory) by adding a recurrent layer which can be used to deal with sequential input patterns and to characterize their temporal relations. RFAM provides a Hebbian-style learning method which establishes the degree of association between input and output. The error back-propagation algorithm is also adopted to train the weights of the recurrent layer of RFAM. To evaluate the performance of the proposed model, we applied it to a word boundary detection problem of speech signal.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Hagan, M.T., Demuth, H.B.: Neural Network Design. PWS Publishing Company (1995)
Connor, J.T., Martin, R.D., Atlas, L.E.: Recurrent Neural Networks and Robust Time Series Prediction. IEEE Transaction on Neural Networks 5(2) (1994)
Cohen, B., Saad, D., Marom, E.: Efficient Training of Recurrent Neural Network with Time Delays. Neural Networks 10(1), 51–59 (1997)
Aussem, A., Murtagh, F., Sarazin, M.: Dyanmical Recurrent Neural Networks Towards Environmental Time Series Prediction. International Journal of Neural Systems 6(2), 145–170 (1995)
Jang, D., Choi, H.: Fuzzy Inference System based on Fuzzy Associative Memory. Journal of Intelligent and Fuzzy Systems 5(3) (1997)
Hebb, D.O.: The Organization of Behavior. John Wiley & Sons, New York (1949)
Wu, G.-D., Lin, C.-T.: Word Boundary Detection with Mel-Scale Frequency Bank in Noisy Environment. IEEE Speech and Audio Processing 8(5), 541–554 (2004)
Wu, G.-D., Lin, C.-T.: A Recurrent Neural Fuzzy Network for Word Boundary Detection in Variable Noise-Level Environments. IEEE Systems, Man and Cybernetics( 2001) 31(1), 84–97 (2001)
Junqua, J.C., Mak, B., Reaves, B.: A robust algorithm for word boundary detection in the presence of noise. IEEE Trans. Speech Audio Processing 2, 406–412 (1994)
Juang, C.F., Lin, C.T.: An on-line self-constructing neural fuzzy inference network and its application. IEEE Trans. Fuzzy System 6, 12–32 (1998)
Jang, J.S.R.: Self-learning fuzzy controllers based on temporal back propagation. IEEE Trans. Neural Networks 3, 714–723 (1992)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Lee, J., Kim, W., Cha, J., Kim, G., Choi, H. (2004). A New Recurrent Fuzzy Associative Memory for Recognizing Time-Series Patterns Contained Ambiguity. In: Laganá, A., Gavrilova, M.L., Kumar, V., Mun, Y., Tan, C.J.K., Gervasi, O. (eds) Computational Science and Its Applications – ICCSA 2004. ICCSA 2004. Lecture Notes in Computer Science, vol 3043. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-24707-4_3
Download citation
DOI: https://doi.org/10.1007/978-3-540-24707-4_3
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-22054-1
Online ISBN: 978-3-540-24707-4
eBook Packages: Springer Book Archive