Abstract
Methods suggested for temporally processing neural networks include recurrent multi-layer perceptrons, the use of capacitive nodes, time dynamic networks and windowing networks. These, along with self-organising temporal neurons suggested by the author, are applied to the problem of morse code recognition and their performances compared. Experimental results show the inadequacy of error back-propagation. The methods of feedback and windowing for temporal recognition are shown to be inferior to neurons that explicitly involve time. It is concluded that further investigation into self-organising temporal neurons should be made.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
Reference
Rumelhart DE, Hinton GE, Williams RJ. Learning internal representations by error propagation. In: Rumelhart DE, McClelland JL, PDP Research Group. Parallel distributed processing. Explorations in the microstructure of cognition. Vol 1 Foundations. MIT Press, 1986, pp 318–362.
Robinson AJ, Fallside F. Static and dynamic error propagation networks with application to speech coding. In: Proceedings of the IEEE conference on neural information processing systems: Natural and synthetic, 1987.
Norrod FE, O’Neill MD, Gat E. Feedback-induced sequentiality in neural networks. Proceedings of the IEEE first international conference on neural networks, 1987.
Stornetta WS, Hogg T, Huberman BA. A dynamical approach to temporal pattern processing. In: Proceedings of the IEEE conference on neural information processing systems: Natural and synthetic, 1987.
Waibel A, Hanazawa T, Hinton G, Shikano K, Lang K. Phoneme recognition using time-delay neural networks. Technical Report TR-1-0006, ATR Interpreting Telephony Laboratories, 1987.
Peeling SM, Moore RK, Varga AP. Isolated digit recognition using the multi-layer perceptron. In: Proceedings of NATO ASI Speech Understanding, 1987.
Hill D. A self-organising temporally processing network for recognition of morse code. In preparation.
Moore R. Computational techniques. In: Bristow G (ed) Electronic speech recognition techniques, technology and applications. Collins, London, 1986, pp 130 ’ 157.
McCulloch N. Personal communication. 1989.
Kohonen T. Self-organizing feature maps. In: Kohonen T Self-organization and associative memory, 2nd Edition, Springer-Verlag, 1987, pp 119–157.
Rumelhart DE, Zipser D. Feature discovery by competitive learning. In: Rumelhart DE, McClelland JL, PDP Research Group. Parallel distributed processing. Explorations in the microstructure of cognition. Vol 1 MIT Press, 1986. pp 151–193.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1992 Springer-Verlag London Limited
About this paper
Cite this paper
Hill, D. (1992). Temporally Processing Neural Networks for Morse Code Recognition. In: Taylor, J.G., Mannion, C.L.T. (eds) Theory and Applications of Neural Networks. Perspectives in Neural Computing. Springer, London. https://doi.org/10.1007/978-1-4471-1833-6_11
Download citation
DOI: https://doi.org/10.1007/978-1-4471-1833-6_11
Publisher Name: Springer, London
Print ISBN: 978-3-540-19650-1
Online ISBN: 978-1-4471-1833-6
eBook Packages: Springer Book Archive