Abstract
This investigation on relationships between the field of artificial neural networks (connectionism) and statistics starts with a look on relevant work based on a classification of possible points of contact. Then follows a distinction between connectionism seen as a tool for data analysis (engineering connectionism) and seen as a model for human thinking or, as one might say, a tool for cognitive or biological modeling (explanatory connectionism). It will be argued that statistics will have a major impact on the former but a rather minor on the latter. As a consequence, the gap between applied neural network research and research concerning cognitive modeling with artificial neural networks will become even bigger than it already is. Statistics will be adopted as the theory of engineering connectionism and therefore entail its development fom a purely empirical to a fullgrown theoretical science. Explanatory connectionism has its own problems and will have to undergo its own changes. Consequently, it will finally be seen as a science of its own independent from mere data analysis purposes.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
Literature
Dorffner, G., Prem, E., Ulbricht, C., Wiklicky, H. (1991), Theory and Practice of Neural Networks, in Brauer, W. & Hernandez, D. (eds.), Verteilte künstliche Intelligenz und kooperatives Arbeiten, Springer Berlin, Informatik-Fachberichte 291.
Dorffner, G. (ed.) (1995), Neural Networks and a New AI, Chapman & Hall, London.
Egmont-Petersen, M., Talmon, J.L., Brender, J., McNair, P. (1994), On the quality of neural net classifiers, Artificial Intelligence in Medicine 6, 359–381.
Finnoff, W., Hergert, F., Zimmermann, H.G. (1992), Improving Generalization Performance by Nonconvergent Model Selection Methods, in Aleksander, I. & Taylor, J. (eds.), Artificial Neural Networks, 2, North-Holland, Amsterdam, pp. 233–236.
Hergert, F., Finnoff, W., Zimmermann, H.G. (1992a), A Comparison of Weight Elimination Methods for Reducing Complexity in Neural Networks, in IJCNN International Joint Conference on Neural Networks, Baltimore, IEEE, pp. 980–987.
Hergert, F., Zimmermann, H.G., Kramer, U., Finnoff, W. (1992b), Domain Independent Testing and Performance Comparisons for Neural Networks, in Aleksander, I. & Taylor, J. (eds.), Artificial Neural Networks, 2, Nort-Holland, Amsterdam, pp. 1071–1076.
Kibler, D. & Langley, P. (1988), Machine Learning as an Experimental Science, Machine Learning, 3(1), 5–8.
Michie, D., Spiegelhalter, D.J., Taylor, C.C. (eds.) (1994), Machine Learning, Neural and Statistical Classification, Ellis Horwood, England.
Paass, G. (1993), Assessing and Improving Neural Network Predictions by the Bootsrap Algorithm, in Hanson, S.J., et al. (eds.), Neural Information Processing Systems 5, Morgan Kaufmann, San Mateo, CA.
Partridge, D. (1987), What's Wrong With Neural Architectures, Computer Science Dept., Univ. of Exeter, Research Report 142, 1987.
Prechelt, L. (1994a), A Study of Experimental Evaluations of Neural Network Learning Algorithms: Current Research Practice, Fakultät für Informatik, Universität Karlsruhe, Technical Report 19/94.
Prechelt, L. (1994b), PROBEN1 — A Set of Neural Network Benchmark Problems and Benchmarking Rules, Fakultät für Informatik, Universität Karlsruhe, Technical Report 21/94.
Prem, E., (1995a), New AI: Naturalness Revealed in the Study of Artificial Intelligence, in Dorffner (1995).
Prem, E., (1995b), Understanding Complex Systems: What can the speaking lion tell us?, in Steels, L. (ed.), The Biology and Technology of Autonomos Agents, Springer, NATO ASI Series.
Ripley, B.D. (1993), Statistical Aspects of Neural Networks, in Barndorff-Nielsen, O.E, Jensen, J.L., Kendall, W.S., (eds.), Networks and Chaos: Statistical and Probabilistic Aspects, London: Chapman & Hall.
Röscheisen, M., Hofmann, R., Tresp. V. (1992), Neural Control for Rolling Mills: Incorporating Domain Theories to Overcome Data Deficiency, in Moody, J.E., et al. (eds.), Neural Information Processing Systems 4, Morgan Kaufmann, San Mateo, CA.
Schaffer, C. (1993), Technical Note: Selecting a Classification Method by Cross-Validation, Machine Learning, 13(1), 135–143.
Shavlik, J.W., Mooney, R.J., Towell, G.G. (1991), Symbolic and Neural Learning Algorithms: An Experimental Comparison, Machine Learning, 6(2).
Sarle, W.S. (1994), Neural Networks and Statistical Models, Proceedings of the Nineteenth Annual SAS Users Group International Conference, Cary, NC: SAS Institute, pp 1538–1550.
Stone, G.O. (1986), An Analysis of the Delta Rule and the Learning of Statistical Associations, in Rumelhart D.E. & McClelland J.L., Parallel Distributed Processing, Explorations in the Microstructure of Cognition, Vol 1: Foundations, MIT Press, Cambridge, MA.
Tresp, V., Ahmad, S., Neuneier, R. (1994), Traininig Neural Networks with Deficient Data, in Cowan, J.D., Tesauro, G., Alspector, J. (eds.), Neural Information Processing Systems 6, Morgan Kaufmann.
Ulbricht, C. (1994), Multi-recurrent Networks for Traffic Forecasting, Proceedings of the AAAI'94 Conference, Seattle, Washington, Volume II, pp. 883–888.
Winston, P.H. (1992), Artificial Intelligence, Addison-Wesley, Reading, MA.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1995 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Flexer, A. (1995). Connectionists and statisticians, friends or foes?. In: Mira, J., Sandoval, F. (eds) From Natural to Artificial Neural Computation. IWANN 1995. Lecture Notes in Computer Science, vol 930. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-59497-3_209
Download citation
DOI: https://doi.org/10.1007/3-540-59497-3_209
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-59497-0
Online ISBN: 978-3-540-49288-7
eBook Packages: Springer Book Archive