9h30-10h00 : Welcoming

Coffee offered by the Solstice ANR Project

Welcoming and program presentation.

What is a Neural Network ? A quick introduction.

10h00-10h45 : Damien Fourure

Transferability.

• Distilling the knowledge in a neural network,G. Hinton, O. Vinyals and J. Dean (NIPS 2014)
• How transferable are features in deep neural networks?, J. Yosinski, J. Clune, Y. Bengio and H. Lipson (NIPS 2014)
• Unsupervised Domain Adaptation by Backpropagation Y. Ganin, V.Lempitsky (ICML 2015)
• Semantic Scene Parsing Using Inconsistent Labellings D. Fourure, R. Emonet, E. Fromont, D. Muselet, A. Tremeau and C. Wolf

10h45-11h00 : Coffee break

Sponsored by Solstice ANR Project (url)

11h00-11h45 : Bastien Moysset

Object Detection with Recurrent Neural Networks.

• Scalable object detection using deep neural networks, D Erhan, C Szegedy, A Toshev, D Anguelov (CVPR 2014)
• Scalable, high-quality object detction, C Szegedy, S Reed, D Erhan, D Anguelov
• Space Displacement Localization Neural Networks to locate origin points of handwritten text lines in historical documents, B Moysset, P Adam, C Wolf, J Louradour (ICDAR 2015 Workshop on Historical Document Processing , 2015)

11h45-13h30 : Lunch

13h30-14h15 : Christian Wolf

DeepLearning vs Random Forests.

• Deep Neural Decision Forest, P. Kontschieder, M. Fiterau, A. Criminisi and S. Rota Bulo (ICCV 2015)
• Structured class-labels in random forests for semantic image labelling,P. Kontschieder, S. Rota Bulo H. Bischof and M. Pelillo (ICCV 2011)
• Neural Decision Forests for Semantic Image Labelling, S. Rota Bulo, P. Kontschieder (CVPR 2014)

14h15-15h00 : Mohamed Elawady

Underwater sparse image classification using deep convolutional neural networks (VIBOT MSc Thesis) [http://www.coralbots.org/]

15h00-15h30 : Coffee break

Sponsored by Solstice ANR Project (url)

15h30-16h15 : Natalia Neverova

• Learning Human Identity from Motion Patterns, N. Neverova, C. Wolf, G. Lacey, L. Fridman, D. Chandra, B. Barbello and G. Taylor
• Hand pose estimation through weakly-supervised learning of a rich intermediate representation, N. Neverova, C. Wolf, F. Nebout and G. Taylor

16h15-17h00 : Rémi Emonet

Abstractions and Frameworks for Deep Learning: a Discussion − Caffe, Torch, Theano, TensorFlow, et al.

17h00-17h30 : Debriefing