Ueli Meier @ IDSIA (original) (raw)

CURRENT

I am a PostDoc Researcher at IDSIA, under supervision of J. Schmidhuber. Main research interest: hierarchical neural networks for feature extraction, unsupervised and supervised feature extraction, pattern recognition, handwritten character recognition. I'm currently working in collaboration with ArcelorMittal on improving detection and classification of steel defects. In the very recent past I worked on an optical character recognition system that automatically extracts and recognizes handwritten inputs form scanned forms.

PAST

• 2008: PostDoc position at Institut de Physique du Globe de Paris (IPGP) with N. Shapiro.
• 2004-2008: PhD (.pdf) at Utrecht University under supervision of A. Curtis and J. Trampert.

PUBLICATIONS Journals:

• Ciresan D., Meier U., Masci J., Schmidhuber J., 2012. Multi Column Deep Neural Network for Traffic Sign Classification, Neural Networks 2012, invited in press.
• Ciresan D., Meier U., Gambardella L.M., Schmidhuber J., 2010. Deep Big Simple Neural Nets For Handwritten Digit Recognition, Neural Computation, 22, 3207-3220. (ArXiv preprint)
• Meier U., Brenguier F., Shapiro N., 2010. Detecting seasonal variations in seismic velocities within Los Angeles basin from correlations of ambient seismic noise, Geophys. J. Int., 181, 985-996, doi: 10.1111/j.1365-246X.2010.04550.x.(.pdf)
• Meier U., Trampert J., Curtis A., 2009. Global variations of temperature and water content in the mantle transition zone from higher mode surface waves, Earth Planet. Sci. Lett., 282, 91-101.(.pdf)
• Meier U., Curtis A., Trampert J., 2007. Global crustal thickness from neural network inversion of surface wave data, Geophys. J. Int., 169, 706-722, doi: 10.1111/j.1365-246X.2007.03373.x.(.pdf)
• Meier U., Curtis A., Trampert J., 2007. Fully nonlinear inversion of fundamental mode surface waves for a global crustal model, Geophys. Res. Let., 34, L16304, doi: 10.1029/2007GL030989.(.pdf)
• Meier U., Curtis A., Trampert J., 2005. Neural networks with an application to global crustal structure, Science and Supercomputing in Europe, HPC-Europe, 353-356.
• Holliger K., Lampe B., Meier U., Lambert M., 2004. Realistic modeling of surface ground-penetrating radar antenna systems: where do we stand?, Near Surface Geophysics, 2, 15-23.

PUBLICATIONS Conferences:

• Ciresan D., Meier U., Schmidhuber J., 2012. MCDNN for Image Classification, CVPR 2012, accepted.
• Ciresan D., Meier U., Schmidhuber J., 2012. Transfer Learning for Latin and Chinese Characters with Deep Neural Networks, IJCNN 2012, accepted.
• Masci J., Meier U., Ciresan D., Schmidhuber J., Fricout G., 2012. Steel Defect Classification with Max-Pooling Convolutional Neural Networks, IJCNN 2012, accepted.
• Ciresan D., Meier U., Gambardella L.M., Schmidhuber J., 2011. Convolutional Neural Network Committees For Handwritten Character Classification, ICDAR 2011, 1250-1254.
• Meier U., Ciresan D., Gambardella L.M., Schmidhuber J., 2011. Better digit recognition with a committee of simple Neural Nets, ICDAR 2011, 1135-1139.(.pdf)
• Schmidhuber J., Ciresan D., Meier U., Masci J., Graves A., 2011. On Fast Deep Nets for AGI Vision, AGI 2011, 243-246.
• Ciresan D.C., Meier U., Masci J., Schmidhuber J., 2011. A Committee of Neural Networks for Traffic Sign Classification, International Joint Conference on Neural Networks.
• Ciresan D.C., Meier U., Masci J., Schmidhuber J., 2011. Flexible, High Performance Convolutional Neural Networks for Image Classification, International Joint Conference on Artificial Intelligence, 1237-1242.
• Masci J., Meier U., Ciresan D.C., Schmidhuber J., 2011. Stacked Convolutional Auto-Encoders for Hierarchical Feature Extraction, International Conference on Artificial Neural Networks, 52-59.