Research Seminars Archives >> 

April 26

15:30 h

Room 55.309

PhD Research Seminar

Experiences by PhD students


  • Ahmed Eladly (BERG) : New technology to restore movement in paralysis
  • Irene Vigué Guix  (MRG):  A mnemonic system based on stimulation-free neuroimaging.
  • Èric Lluch (Physense):  Meshless method for cardiac mechanics modelling
  • Alp Öktem (TALN):  Generating punctuation in Transcribed Speech: Combining lexical and prosodic features using parallel recurrent neural networks 

May 8

15:30 h

Room 55.309

Invited Research Seminar

Learning Deep Networks from ranked data

By Joost van de Weijer 


In the second part of the talk I will discuss two applications of the decomposition of fully connected layers into several layers.  Deep Neural Networks trained on large datasets can be easily transferred to new domains with far fewer labeled examples by a process called fine-tuning. However, networks designed to be optimal for the source task are often prohibitively large for the target task. We show how layer decomposition can be used to effectively compress the network. In addition, we will show how layer decomposition can be used for the task of learning without forgetting where the task is to learn new tasks without forgetting previously learned tasks. We will show how this can be used to improve the diagonal assumption underlying the Fisher information matrix for the Elastic Weight Consolidation algorithm. The work in this talk is presented at ICCV 2017 and CVPR 2018.


Joost van de Weijer is  the leader of the Learning and Machine Perception Team (LAMP) and a senior researcher at the Computer Vision Center (Universitat Autònoma de Barcelona). His main research interest is in applying color imaging theory to the field of computer vision: color constancy, color naming, object recognition, recoloring algorithms, color feature detection and color feature extraction.

If the seminar is ofered via streaming in: 

- Room 55.309 or 55.410 follow this link

- Auditorium follow this link

If you are interested in giving a Research Seminar or you would like to invite a speaker please fill in the following form RSDetails Form .