Efficient training of time delay neural networks for sequential patterns

Neurocomputing

Volumn 10, Issue 1, 1996, Pages 33-42

  Cancelliere, Rossella ^a,b   Gemello, Roberto ^a  

^a CSELT   (Italy)

^b UNIVERSITY OF TURIN   (Italy)

Author keywords

Efficient training; Sequential patterns; TDNN

Indexed keywords

BACKPROPAGATION; COMPUTATIONAL COMPLEXITY; ERROR ANALYSIS; LEARNING ALGORITHMS; PATTERN RECOGNITION;

SEQUENTIAL PATTERNS; TIME DELAY NEURAL NETWORKS (TDNN);

FEEDFORWARD NEURAL NETWORKS;

ALGORITHM; ARTICLE; ARTIFICIAL NEURAL NETWORK; PRIORITY JOURNAL; RECOGNITION; TRAINING;

EID: 0030031159     PISSN: 09252312     EISSN: None     Source Type: Journal    
DOI: 10.1016/0925-2312(95)00044-5     Document Type: Article

References (9)

1. S.P. Day and M.R. Davenport, Continuous-time temporal backpropagation with adaptable time delays, IEEE Trans. Neural Networks 4 (1993) 348-354.
2. J.L. Elman, Finding structure in time, CRL Technical Report No. 8801, La Jolla University of California, San Diego, 1988.
3. P. Haffner and A. Waibel, Time-Delay Neural Networks embedding time alignment: a performance analysis, in Proc. Eurospeech '91, Vol. 3 Geneva, (Sep. 1991) 1415-1418.
4. K. Hornik, M. Stinchcombe and H. White, Multilayer feedforward networks are universal approximators, in Neural Networks 359-366 (1989).
5. M. Miyatake, H. Sawai, Y. Minami and K. Shikano, Integrated training for spotting Japanese phonemes using large phonemic time-delay neural networks, in Proc. ICASSP '90 (Apr. 1990) 449-452.
6. D.E., Rumelhart, G.E. Hinton and R.J. Williams, Learning internal representations by error propagation, in Parallel Distributed Processing: Explorations in the Microstructure of Cognition, Vol. 1 (Cambridge, MA MIT Press, 1986) 318-362.
7. A. Waibel, T. Hanazawa, G. Hinton, K.J. Lang and K. Shikano, Phoneme recognition using time-delay neural networks, IEEE Trans. Acoust. Speech Signal Processing 37 (Mar. 1989) 328-339.
8. E.A. Wan Temporal backpropagation for FIR neural networks, Int. Joint Conf. Neural networks, San Diego, CA (June 1990) 575-580.
9. R.J. Williams and D. Zipser, A learning algorithm for continuously running fully recurrent neural networks, Neural Computat., 1 (1989) 270-280.