Neural networks and computing

In this paper, we give a general presentation of neural networks, showing their links and differences with Artificial Intelligence and neurosciences. We provide the general formalism of neural networks and describe two neural networks learning algorithms: gradient backpropagation and learning vector quantization. We then illustrate the behavior of these algorithms on a particular application in speech processing. We then discuss what a neural networks programming environment should provide and present some of the existing commercial products. We end the paper by the presentation of MimeNice, which is an example of such an environment developed within the Esprit Pygmalion-Galatea projects.

[1]  P. Treleaven,et al.  THE PYGMALION NEURAL NETWORK PROGRAMMING ENVIRONMENT , 1990 .

[2]  Sylvie Thiria,et al.  Multi-Module Neural Networks for Classification , 1990 .

[3]  L. Bottou,et al.  Galatea: A C-Library for Connectionist Applications , 1990 .

[4]  R Linsker,et al.  From basic network principles to neural architecture: emergence of spatial-opponent cells. , 1986, Proceedings of the National Academy of Sciences of the United States of America.

[5]  Shigeru Katagiri,et al.  Shift-invariant, multi-category phoneme recognition using Kohonen's LVQ2 , 1989, International Conference on Acoustics, Speech, and Signal Processing,.

[6]  Misha Mahowald,et al.  A silicon model of early visual processing , 1993, Neural Networks.

[7]  T. Kohonen,et al.  Statistical pattern recognition with neural networks: benchmarking studies , 1988, IEEE 1988 International Conference on Neural Networks.

[8]  James L. McClelland,et al.  James L. McClelland, David Rumelhart and the PDP Research Group, Parallel distributed processing: explorations in the microstructure of cognition . Vol. 1. Foundations . Vol. 2. Psychological and biological models . Cambridge MA: M.I.T. Press, 1987. , 1989, Journal of Child Language.

[9]  Stephen Grossberg,et al.  Studies of mind and brain , 1982 .

[10]  Geoffrey E. Hinton,et al.  Phoneme recognition using time-delay neural networks , 1989, IEEE Trans. Acoust. Speech Signal Process..

[11]  Teuvo Kohonen,et al.  Self-Organization and Associative Memory, Third Edition , 1989, Springer Series in Information Sciences.

[12]  Kurt Hornik,et al.  Multilayer feedforward networks are universal approximators , 1989, Neural Networks.