ESPRIT II is currently funding two major neural computing projects: Project 2059: PYGMALION and Project 2092: ANNIE.
The objectives of PYGMALION are: firstly to demonstrate to European industry the potential of neural networks for various applications; secondly to develop a European neural network programming system, language and algorithm library; and thirdly to promote exchange of neural computing information in the European research community.
This paper introduces the PYGMALION project, reviews the neural network applications in image & speech processing, and then describes the neural network programming environment.
KeywordsNeural Network Dynamic Time Warping Neural Computing Automatic Speech Recognition System European Industry
Unable to display preview. Download preview PDF.
- 1.New Science Associates Inc., “Neural Networks: Prospects for Commercial Use,” New Sciences Associates. South Norwalk. CT, Spring 1988.Google Scholar
- 2.R.P Lippmann, “An Introduction to Computing with Neural Nets,” IEEE ASSP Magazine, pp. 4–22, April 1987.Google Scholar
- 3.D.E. RUMELHART, G.E. HINTON, and R.J. WILLIAMS, “323:533–536, (1986),” in Neurocomputing, Foundations of Research,” pp. 675–700.Google Scholar
- 4.T. Kohonen, “Self-Organisation and Associative Memory,” Springer-Verlag Berlin, 1984.Google Scholar
- 5.B. Gold and R.P. Lippmann, “A Neural Network for isolated word recognition,” IEEE ICASSP. pp. 44 – 47, 1988.Google Scholar
- 6.B.W. Kernighan and D.M Ritchie, The C Programming Language Second Edition.Prentice Hall, 1988.Google Scholar
- 7.J. Martin, “Fourth-Generation Languages”.Prentice Hall, 1985.Google Scholar
- 8.Krause A, Hackbarth H (1989) Scaly artificial neural networks for speaker-independent recognition of isolated words. IEEE ICASSP (S1): 21–24Google Scholar