Abstract
When attempting to apply neural networks to real-world problems one is confronted with a major problem — there is no general theory about which network model to choose and how to optimally set all parameters. The large number of publications on neural networks is in strong contrast to a lack of means for comparison between, and appraisal of different systems found in literature. Furthermore, most existing applications focus on simple associative multi-layer architectures that are not suitable for many aspects of real-world problems, such as time-dependencies between inputs.
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.
References
Ahalt S.C., Chen P., Krishnamurthy A.K.: Performance Analysis of Two Image Vector Quantization Techniques, in Proceedings of the International Joint Conference on Neural Networks, I-169–I-175, 1989.
Dehaene S., Changeux J., Nadal J.: Neural networks that learn temporal sequences by selection, Proc. Natl Acad. Sci USA, Vol. 84, pp. 2727–2731, 1987.
Elman J.L.: Finding Structure in Time, Cognitive Science, 1990.
Hataoka N., Waibel A.H.: Speaker-Independent Phoneme Recognition on TIMIT Database Using Integrated Time-Delay Neural Networks (TDNNs), in International Joint Conference on Neural Networks, San Diego, IEEE, Volume I, pp. 57–62, 1990.
Jordan M.I.: Attractor dynamics and parallelism in a connectionist sequential machine, in Proceedings of the Eight Annual Conference of the Cognitive Science Society, Erlbaum, Hillsdale, NJ, pp. 531–546, 1986.
Mannes C., Dorffner G.: Self-Organizing Detectors of Spatio-Temporal Patterns, in Kindermann J., Linden A. (eds.): Distributed Adaptive Neural Information Systems, Oldenbourg, Muenchen/Wien, pp. 89–102, 1990.
McClelland J.L., Elman J.L.: Interactive Processes in Speech Perception: The TRACE Model, in Rumelhart D.E., McClelland J.L. (eds.): Parallel Distributed Processing, Vol 1, MIT Press, Cambridge, MA, 1986.
Norrod F.E., O’Neill M.D., Gat E.: Feedback-Induced Sequentially in Neural Networks, in Caudill M., Butler C.(eds.), IEEE First International Conference On Neural Networks, San Diego, IEEE, 1987.
Prem E.: A Description Framework for Solving the “Theory Problem” in Connectionism, Master’s Thesis at the Dept. of Medical Cybernetics and Artificial Intelligence, University of Vienna, 1991.
Simpson P.K.: Artificial Neural Systems, Pergamon Press, 1990.
Smith A.W., Zipser D.: Encoding Sequential Structure: Experience with the Real-Time Re-current Learning Algorithm, in IEEE International Conference On Neural Networks, Washington D.C., IEEE, Volume I, pp. 645–648, 1989.
Wan E.A.: Temporal Backpropagation: An Efficient Algorithm for Finite Impulse Response Neural Networks, in Touretzky D.S., et al.(eds.), Connectionist Models, Morgan Kaufmann Publishers, San Mateo, CA, pp. 131–137, 1990.
Wolf L.: Recurrent Nets for the Storage of Cyclic Sequences, in Kosko B.(ed.), IEEE International Conference On Neural Networks, San Diego, IEEE, Volume I, pp. 53–60, 1988.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1991 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Dorffner, G., Prem, E., Ulbricht, C., Wiklicky, H. (1991). Theory and Practice of Neural Networks. In: Brauer, W., Hernández, D. (eds) Verteilte Künstliche Intelligenz und kooperatives Arbeiten. Informatik-Fachberichte, vol 291. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-76980-1_45
Download citation
DOI: https://doi.org/10.1007/978-3-642-76980-1_45
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-54617-7
Online ISBN: 978-3-642-76980-1
eBook Packages: Springer Book Archive