Doing Sequence Analysis by Inspecting the Order in which Neural Networks Learn
The worldwide interest in artificial neural networks that has emerged during the 1980’es has its origins in the dual nature of neural networks: they belong to the class of non-linear dynamical systems, but can also be used as general modeling devices for such systems. Non-linear dynamical systems have traditionally been extremely difficult to model, theoretically or experimentally.
KeywordsTyrosine Glycine Serine Proline Carbonyl
Unable to display preview. Download preview PDF.
- Brunak, S., Engelbrecht, J. & Knudsen, S. (1990). Prediction of human mRNA donor and acceptor sites from the DNA sequence, Preprint, November 1990.Google Scholar
- Chreighton T.E. (1984). Proteins — Structures and Molecular Properties, Freeman, New York.Google Scholar
- Lapedes, A., Barnes, C., Burks, C., Farber, R. & Sirotkin, K. (1990) “Application of Neural Networks and Other Machine Learning Algorithms to DNA Sequence Analysis.” The Proceedings of the Interface Between Computation Science and Nucleic Acid Sequencing Workshop, Dec. 1988 in Santa Fe, New Mexico. Eds. G.I. Bell and T.G. Marr. Proceedings of the Santa Fe Institute vol. VII, 157–182, Addison-Wesley.Google Scholar
- Minsky, M. & Papert, S. (1969, 1988). Perceptrons. MIT Press, Cambridge, Massachusetts.Google Scholar
- Rosenblatt, F. (1962). Principles of Neurodynamics. Spartan Books. New York.Google Scholar
- Rumelhart, D.E., Hinton, G.E. & Williams, R.J. (1986) In Rumelhart, D.E., McClelland, J.L. and the PDP Research Group (eds.), Parallel Distributed Processing: Explorations in the Microstructure of Cognition. MIT Press, Cambridge, Massachusetts, vol. I, 318–362.Google Scholar
- Sejnowski, T.J. & Rosenberg, C.R. (1987). Parallel Networks that Learn to Pronounce English Text. Complex Systems 1, 145–168.Google Scholar