Machine Learning for a
better World

Mindlab UNAL research group has been a center of excellence for Machine Learning  research, teaching, theory, and practice since its founding in 2001. The research in our group is very broad, and we are interested in all aspects of machine learning. Particular strengths of the group are in multimodal learning and fusion, large scale machine learning and approachs that combine probabilistic models and deep learning.

Natural Language Processing

  •  Question answering for information retrieval and entity extraction
  •  Author profiling for determining a social group of an unknown author
  •  Source code analysis for automated testing of source code

Computer Vision For Medical Image Analysis

  •  Automatically find patterns related with pathology signatures associated with healthy and abnormal tissues
  •  Automatic evaluation of the disease in Ophthalmic images

Multimodal Learning

  •   Models for learning an intermediate representation through multimodal information fusion
  •   takes advantage of additional information provided by multimodal data, and combining them, using data fusion techniques to improve information retrieval performance

Hybrid Deep Kernel Methods

  •   Obtain effective and efficient kernel methods that compete on par with deep learning
  •  Methods for learning a mapping between the features of the input sample and the labels, which is later used to predict labels for unannotated instances



“AI winters were not due to imagination traps, but due to lack of imaginations. Imaginations bring order out of chaos. Deep learning with deep imagination is the road map to AI springs and AI autumns.” – Amit Ray

Come and ride with us!

Fabio A. González, PhD
Computing Systems and Industrial Engineering Dept.
National University of Colombia