Welcome to the information management and processing group

The Information Management and Processing Group (G2PI) belongs to the Department of Signal Theory and Communications of Carlos III University of Madrid. Our group credited experience of over 15 years in R & D, innovation and technology transfer in the field of machine learning and its applications to analysis and information processing.


Machine Learning is one of the backbones that articulates the research activities of the G2PI. Since the foundation of the group, we have been a reference in Spain as early adopters and developers of cutting edge machine learning technologies, such as neural networks in the early 90's, kernel methods (SVMs, Gaussian Processes, Spectral clustering) since the late 90's, boosting and ensembles of committees since the early 2000s and the current bayesian inference methods and multivariate analysis.


Acoustic Echo Cancellation

The group has a solid experience in techniques for statistical signal processing and time series analysis. Apart from our background with classic tools such as ARMA models, array beamforming, or adaptive filters, we have actively developed in the recent years new algorithms based on state-of-the-art kernel and Bayesian learning.  Among other applications, we have successfully applied our designs in acoustics, communications, forecasting, and distributed estimation in wireless networks.

Our research in sensor networks is focused on providing Sensor Networks advanced capabilities to make autonomous and intelligent decisions. Our work is centered on the optimization of the energy resources of nodes and also on the problem of optimizing overall network performance even though sensor nodes make their own decisions based on local information.


We have experience in learning applications dealing with text, audio, and video data. In particular, together with leading companies in the sector, we have applied our designs to music genre recognition, semantic video analysis, or event detection in sport videos. We have also built video recommender systems based on collaborative filtering techniques.


The group does research in  machine learning applications in magnetic resonance imaging (MRI) of the human brain, particularly in spectroscopic, structural and functional MRI. In particular, the group develops techniques for detection and characterization of mental disorders and techniques for functional brain mapping different from standard SPM.