Deep Neural Networks for Industrial Applications

The CPU/GPU software for training and testing Deep Neural Networks I have developed starting from 2008 is state of the art for segmented object classification (see publications, benchmarks and competitions on main page). Some of its details are presented in my papers. It also contains unpublished work.

THIS IS THE FIRST EVER1,2 DEEP NEURAL NETWORK FULLY IMPLEMENTED ON GPU (CUDA).

THIS DNN WON FIVE INTERNATIONAL COMPETITIONS ON IMAGE CLASSIFICATION, DETECTION AND SEGMENTATION.


NEW! - Check my demo and attend my presentation at NVIDIA Booth #1727, SC 2014, November 17-20, New Orleans, Louisiana

NEW! - CUDA Spotlight

NEW! - Check talk S4636 at GTC 2014, March 24-27, San Jose, California

Features:

Ready for deployment in industrial applications like:

Only direct contacts will be considered.





[1] D. Ciresan et al. - Deep, Big, Simple Neural Nets for Handwritten Digit Recognition, Neural Computation, 2010

[2] D. Ciresan et al. - Flexible, High Performance Convolutional Neural Networks for Image Classification, IJCAI, 2011