Siamese Networks for Few Shot Learning



News and Events 

Siamese Networks for Few Shot Learning

On December 16th at 16:00, Room A-123.


Machine learning, and especially deep learning, has achieved state-of-the-art performance in a variety of applications using large databases. However, these algorithms break down when forced to make predictions with little supervised information.

This problem, also known as few shot learning, can be properly addressed by Siamese Networks, which are based on an architecture that computes similarities among highly semantic features representations.


Carlos R. del Blanco received the Telecommunication Engineering and Ph.D. degrees in telecommunication from the Universidad Politécnica de Madrid (UPM), Madrid, Spain, in 2005 and 2011, respectively. Since 2005, he has been a member of the Image Processing Group, UPM. Since 2011, he has also been a member of the faculty of the ETS Ingenieros de Telecomunicacion as an Assistant Professor of ´ signal theory and communications at the Department of Signals, Systems, and Communications. His professional interests include signal and image processing, computer vision, pattern recognition, machine learning, and stochastic dynamic models.


2019 01 11 10.24.40